A computing power routing method, system, device, medium and program product

Abstract

The application provides a computing power routing method, system, device, medium and program product. The method comprises: collecting computing power node entry gateway information and computing power node information connected with an exit gateway; determining a computing network view according to the collected computing power node entry gateway information and computing power node information connected with the exit gateway, the computing network view comprising: a mapping relationship between the entry gateway, the exit gateway and the computing power node information; wherein the computing network view is used to make a computing power routing decision. In the application, the network controller not only collects the complete mapping relationship from the entry gateway to the exit gateway and then to the computing power state information, but also determines the computing network view through the mapping relationship, further introduces the computing power information into the network, comprehensively considers the network information and the computing power information when making the routing decision, performs joint optimization, generates a more reasonable routing strategy, and routes the service request to the best service node along the best path.

Description

Technical Field

[0001] This application relates to the field of data communication network technology, and in particular to a computing power routing method, system, device, medium, and program product. Background Technology

[0002] In current networks, different routing decision schemes have emerged based on the methods and locations of computing power information perception and routing decisions. In both centralized and hybrid schemes, computing power information is obtained through the cloud management system and sent to the network controller. This means the cloud management system only maintains information about computing power nodes, while the network controller only maintains the mapping relationship from the ingress gateway to the egress gateway. The cloud and network management systems are independent, and their information cannot be shared, making joint optimization and scheduling of computing power and the network difficult. Joint optimization and scheduling requires comprehensive consideration of network information from the ingress gateway to the egress gateway, network information from the egress gateway to the computing power nodes, and computing power node information. However, existing centralized and hybrid schemes do not consider the mapping relationship between computing power nodes and egress gateways. Neither the controller nor the cloud management system is aware of this mapping relationship, and when the controller or ingress gateway makes decisions, joint optimization and scheduling of computing power and the network becomes difficult. Summary of the Invention

[0003] This application provides a computing power routing method, system, device, medium, and program product to solve the problem that existing computing power and networks are difficult to jointly optimize and schedule.

[0004] To solve the above-mentioned technical problems, this application is implemented as follows:

[0005] In a first aspect, embodiments of this application provide a computing power routing method, including:

[0006] Collect information on the ingress gateway and computing node information of the computing power nodes connected to the egress gateway;

[0007] Based on the collected information on the ingress gateway and computing node information of the computing power nodes connected to the egress gateway, a computing network view is determined. The computing network view includes the mapping relationship between the ingress gateway, egress gateway, and computing node information.

[0008] The computing network view is used to make computing power routing decisions.

[0009] Optionally, the collection of ingress gateway information and computing node information of the computing power nodes connected to the egress gateway includes:

[0010] Receive information about the ingress gateway of the computing power node connected to the egress gateway, wherein the ingress gateway information of the computing power node includes at least: the egress gateway and the IP address of the computing power node ingress gateway;

[0011] Receive computing power node information, which includes: the IP address of the computing power node's ingress gateway and the computing power node's status information.

[0012] Optionally, the computing power node entry gateway information may also include anycast address IP, wherein the anycast address IP is used to identify the same type of service;

[0013] The computing network view also includes the mapping relationship between the computing power node information and different services.

[0014] Optionally, receiving the ingress gateway information of the computing node connected to the egress gateway includes:

[0015] Based on the extended distributed routing protocol, the ingress gateway information of the computing power node is received;

[0016] The extended distributed routing protocol is an extended border gateway protocol link state protocol. The extended border gateway protocol link state protocol includes the path attribute of the extended border gateway protocol link state protocol. The path attribute is used to announce the topology information of the connected computing power nodes, and carries at least the ingress gateway IP of the computing power node.

[0017] Optional, also includes:

[0018] Based on the computing network view, the weight information of the computing power nodes is determined, and the weight information is used to formulate computing power routing decisions;

[0019] The weight information of the computing power nodes is sent to the ingress gateway or the scheduling domain, wherein the scheduling domain includes at least one ingress gateway.

[0020] Optionally, determining the weight information of computing nodes based on the computing network view further includes:

[0021] For each of the aforementioned entry gateways, determine whether the number of computing nodes for each type of service is greater than or equal to 2;

[0022] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the entry gateway;

[0023] If the number of computing power nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing power nodes;

[0024] or,

[0025] Generate the scheduling domain;

[0026] For each of the scheduling domains, determine whether the number of computing nodes for each type of service is greater than or equal to 2;

[0027] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the scheduling domain;

[0028] If the number of computing nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing nodes.

[0029] Optionally, after sending the weight information of the computing power nodes to the ingress gateway or scheduling domain, the method further includes:

[0030] If the computing power node information or service deployment changes, determine whether it is necessary to regenerate and distribute the weight information of the computing power node, wherein the service deployment is associated with the computing power node information and the computing power node ingress gateway information connected to the egress gateway;

[0031] If it is necessary to regenerate and distribute the weights, the computing network view is regenerated based on the changed computing node information or service deployment, and the computing node ingress gateway information connected to the egress gateway.

[0032] Based on the regenerated computing network view, the weight information of the computing power nodes is regenerated and sent to the ingress gateway or scheduling domain.

[0033] Secondly, embodiments of this application provide a method for computing power routing, including:

[0034] Receive the weight information of computing power nodes, the weight information is determined based on the computing network view, the computing network view includes: the mapping relationship between the ingress gateway, the egress gateway and the computing power node information;

[0035] Based on the weight information, a computing power routing decision is made.

[0036] Thirdly, embodiments of this application provide a computing power routing system, including:

[0037] The data module is used to collect information about the ingress gateway and computing nodes connected to the egress gateway.

[0038] The computing network module is used to determine the computing network view based on the collected information on the ingress gateway and computing node information of the computing power nodes connected to the egress gateway. The computing network view includes the mapping relationship between the ingress gateway, egress gateway and computing node information.

[0039] The computing network view is used to make computing power routing decisions.

[0040] Fourthly, embodiments of this application provide an electronic device, including: 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, it implements the steps of the computing power routing method described in the first aspect above.

[0041] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the computing power routing method described in the first aspect above.

[0042] In a sixth aspect, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the computing power routing method as described in the first aspect above.

[0043] In this application, by collecting the ingress gateway information and computing node information of the computing nodes connected to the egress gateway, and based on the collected ingress gateway information and computing node information of the computing nodes connected to the egress gateway, a computing network view is determined, thereby obtaining the mapping relationship between the ingress gateway, egress gateway, and computing node information. In this embodiment, the controller not only maintains the mapping relationship from the ingress gateway to the egress gateway, but also collects the ingress gateway information and computing node information of the computing nodes connected to the egress gateway, and further determines the computing network view. The mapping relationship between the ingress gateway, egress gateway, and computing node information in the computing network view provides a basis for joint optimization scheduling of computing power and network. Unlike the prior art, where neither computing power nor network considers the mapping relationship between computing nodes and egress gateways, in this application, the network controller not only collects the complete mapping relationship from the ingress gateway to the egress gateway and then to the computing power status information, but also determines the computing network view through this mapping relationship, further introducing computing power information into the network. When making routing decisions, network information and computing power information are comprehensively considered for joint optimization, generating a more reasonable routing strategy, and routing service requests along the optimal path to the optimal service node. Attached Figure Description

[0044] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0045] Figure 1 This is a schematic diagram of a distributed computing power information sensing method in the prior art;

[0046] Figure 2 This is a schematic diagram of a centralized service topology generation method in the prior art;

[0047] Figure 3 This is a schematic diagram of another centralized service topology generation method in the prior art;

[0048] Figure 4 This is a flowchart of a computing power routing method provided in an embodiment of this application;

[0049] Figure 5 This is a schematic diagram of generating a network view provided in an embodiment of this application;

[0050] Figure 6 This is a schematic diagram of an extended BGP-LS path attribute provided in an embodiment of this application;

[0051] Figure 7 This is a schematic diagram illustrating the generation of computing power node weights according to an embodiment of this application;

[0052] Figure 8 This is a schematic diagram of another computing power routing method provided in an embodiment of this application;

[0053] Figure 9 This is a schematic diagram of the structure of a computing power routing system provided in an embodiment of this application;

[0054] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0055] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0056] Currently, different routing strategies have emerged depending on the method of sensing computing power information, the location of the sensing, and the location of computing power routing decisions.

[0057] Please refer to Figure 1 Distributed: Computing power information is advertised between network nodes through routing protocols, and routing decisions are made at the entry node;

[0058] Please refer to Figure 2 and Figure 3 Centralized: Computing power information is sent to the network controller through the cloud management system. The network controller makes centralized decisions and distributes routing policies to the routers.

[0059] Hybrid: Computing power information is sent to the network controller through the cloud management system. The network controller then distributes the computing power information to the entry node, and the entry node decides the routing strategy.

[0060] However, in existing technologies, the mapping relationship between the egress gateway and the computing nodes is not considered when making routing decisions.

[0061] Furthermore, since traditional routing protocols are triggered by changes in network state, if computing power information is transmitted in a distributed routing protocol, the different change cycles of the two will cause routing protocol oscillations and non-convergence, affecting the existing routing system. Therefore, in the routing system, it is necessary to consider how to minimize the impact on the existing system while still achieving distributed computing network joint computing. Therefore, to avoid the above problems, the computing power information in this application is not announced between network nodes through the routing protocol, but is reported to the controller. Specifically...

[0062] Please refer to Figure 4 This application provides a computing power routing method, including:

[0063] Step 11: Collect information on the ingress gateway and computing node information of the computing nodes connected to the egress gateway;

[0064] Step 12: Based on the collected information on the ingress gateway and computing node connected to the egress gateway, determine the computing network view, which includes the mapping relationship between the ingress gateway, egress gateway, and computing node information;

[0065] The computing network view is used to make computing power routing decisions.

[0066] In this application, by collecting the ingress gateway information and computing node information of the computing nodes connected to the egress gateway, and based on the collected ingress gateway information and computing node information of the computing nodes connected to the egress gateway, a computing network view is determined, thereby obtaining the mapping relationship between the ingress gateway, egress gateway, and computing node information. In this embodiment, the controller not only maintains the mapping relationship from the ingress gateway to the egress gateway, but also collects the ingress gateway information and computing node information of the computing nodes connected to the egress gateway, and further determines the computing network view. The mapping relationship between the ingress gateway, egress gateway, and computing node information in the computing network view provides a basis for joint optimization scheduling of computing power and network. Unlike the prior art, where neither computing power nor network considers the mapping relationship between computing nodes and egress gateways, in this application, the network controller not only collects the complete mapping relationship from the ingress gateway to the egress gateway and then to the computing power status information, but also determines the computing network view through this mapping relationship, further introducing computing power information into the network. When making routing decisions, network information and computing power information are comprehensively considered for joint optimization, generating a more reasonable routing strategy, and routing service requests along the optimal path to the optimal service node.

[0067] Furthermore, it is also necessary to consider how to send the above mapping relationship to the controller so that it can perform integrated network and path calculation.

[0068] Optionally, the collection of ingress gateway information and computing node information of the computing power nodes connected to the egress gateway includes:

[0069] Receive information about the ingress gateway of the computing power node connected to the egress gateway, wherein the ingress gateway information of the computing power node includes at least: the egress gateway and the IP address of the computing power node ingress gateway;

[0070] Receive computing power node information, which includes: the IP address of the computing power node's ingress gateway and the computing power node's status information.

[0071] Optionally, the controller receives the ingress gateway information of the computing node connected to the egress gateway from the egress gateway. That is, the egress gateway sends the ingress gateway information of the computing node connected to the egress gateway, including (egress gateway, computing node ingress gateway IP).

[0072] Optionally, the computing node information received by the controller comes from the cloud management system. In other words, the cloud management system sends computing node information to the controller, including the computing node's entry gateway IP and computing status information.

[0073] Please refer to Figure 5 Optionally, the controller maps the data from the egress gateway to the computing power status information based on the "computing power node ingress gateway IP" (egress gateway, computing power node ingress gateway IP, anycast IP, computing power status information). Then, combining the mapping relationship between the ingress gateway and the egress gateway, a computing network view is formed containing a complete mapping relationship from the ingress gateway to the egress gateway and then to the computing power status information. The computing network view includes the ingress gateway, egress gateway, computing power node ingress gateway IP, and computing power status information. It is worth noting that in this application... Figure 5 For illustrative purposes, the mapping relationships between some computing nodes and gateways have been omitted.

[0074] Optionally, computing power routing needs to select the optimal node among multiple nodes providing the same service while considering the network path. Therefore, anycast addresses are introduced to identify the same service, and computing power routing maps anycast addresses to real IP addresses.

[0075] Optionally, the computing power node entry gateway information may also include anycast address IP, wherein the anycast address IP is used to identify the same type of service;

[0076] The computing network view also includes the mapping relationship between the computing power node information and different services.

[0077] Optionally, the mapping relationship between anycast and the real IP can be obtained by establishing a BGP peer (Border Gateway Protocol peer) between the computing node's ingress gateway and the computing power routing egress gateway. Establishing a BGP peer relationship allows devices to exchange routing information, enabling inter-network routing and traffic transmission. When sending the ingress gateway information of the computing node connected to the egress gateway, the egress gateway will also send the anycast IP. Please refer to [reference needed]. Figure 6 Furthermore, anycast IP addresses can identify services of the same type, and a network view can be constructed that includes mappings between computing node information and different services. Identifying services of the same type via anycast IP addresses enables automatic routing of user requests to the nearest or optimal node providing that service, enhancing service availability, load balancing, and response speed. It also improves network fault tolerance and resource utilization efficiency, contributing to a better overall user experience.

[0078] Optionally, in some embodiments, the mapping relationship is reported through the extended Border Gateway Protocol Link-State (BGP-LS) protocol. The BGP-LS protocol is mainly used to distribute network topology information through the Border Gateway Protocol (BGP), enabling the transmission of egress gateway information to the controller for a more comprehensive understanding of the connectivity and status of the entire network.

[0079] Optionally, receiving the ingress gateway information of the computing node connected to the egress gateway includes:

[0080] Based on the extended distributed routing protocol, the ingress gateway information of the computing power node is received;

[0081] The extended distributed routing protocol is an extended border gateway protocol link state protocol. The extended border gateway protocol link state protocol includes the path attribute of the extended border gateway protocol link state protocol. The path attribute is used to announce the topology information of the connected computing power nodes, and carries at least the ingress gateway IP of the computing power node.

[0082] Optionally, in some embodiments, please refer to Figure 6The extended BGP-LS in this embodiment defines a BGP Network Layer Reachability Information (NLRI) type, including node information, link information, and IP prefixes. Furthermore, a new type is defined in the BGP-LS path attribute, which is an optional non-transitive attribute. It encodes the object's attributes (links, nodes, and prefixes). Specifically, the extended BGP-LS path attribute specifies the topology information used to advertise connected computing nodes in the BGP-LS attributes, defining a new Type-Length-Value (TLV) that carries the ingress gateway IP of the connected computing node and the configured anycast IP address.

[0083] In this embodiment of the application, by receiving the ingress gateway information of the computing power node based on the extended distributed routing protocol, the status of computing resources can be dynamically and efficiently updated and propagated, enabling the network to intelligently select the best path to allocate user requests, optimize resource utilization, and improve service quality.

[0084] Optionally, in this embodiment, the controller formulates computing power routing decisions based on the computing network view and directly distributes the routing decisions to each ingress gateway. The controller's formulation of computing power routing decisions based on the computing network view and direct distribution of these decisions to each ingress gateway enables global optimization, rapid response, load balancing, and fault recovery, effectively improving network performance and resource utilization. Simultaneously, it simplifies management, enhances security, ensures the implementation of unified policies and dynamic adjustment capabilities, and is suitable for complex, large-scale network environments.

[0085] Existing centralized and hybrid solutions do not consider the mapping relationship between computing nodes and egress gateways. Neither the controller nor the cloud management system is aware of this mapping relationship. Therefore, this application proposes a specific method to achieve topology mapping through the above embodiments.

[0086] When traditional network controllers have Traffic Engineering Requirements (TE) requirements, they assign weights to multiple network paths to the ingress gateway, which then selects the specified path to implement the TE function. For Best Effort Traffic (BE) requirements, the ingress gateway makes its own decision on forwarding. Often, most traffic is BE traffic, while TE is used for some high-priority or value-added services.

[0087] Analogous to the above scheme, in the centralized scenario of computing power routing, the ingress gateway in the TE scenario is issued by the controller with the path and destination node selection strategy; however, in the BE scenario, the ingress gateway is unaware of the status information of computing power nodes, etc., and cannot support the BE scheme of computing network joint scheduling. For business requests that require joint scheduling, they can only be sent to the controller, which will bring performance burden to the controller.

[0088] Based on the above embodiments, this application also provides some embodiments based on weight distribution from a global view. That is, the routing decision is made by the ingress gateway or the scheduling domain. The controller does not distribute a complete computing network view, but distributes the weight values ​​of the ingress gateways of each computing power node corresponding to the same anycast IP. The computing power weight information is combined at the ingress gateway side to realize BE forwarding.

[0089] Optionally, in some embodiments, it further includes:

[0090] Based on the computing network view, the weight information of the computing power nodes is determined, and the weight information is used to formulate computing power routing decisions;

[0091] Optionally, the weight information includes the egress gateway, the IP address of the ingress gateway of the computing power node, and the weight value corresponding to the computing power node.

[0092] The weight information of the computing power nodes is sent to the ingress gateway or the scheduling domain, wherein the scheduling domain includes at least one ingress gateway.

[0093] Optionally, in this embodiment, the generation and distribution of weight information are divided into two granularities: weight generation and distribution at the ingress gateway level and weight generation and distribution at the scheduling domain level. In computing power routing, the number of computing power nodes covered by an ingress gateway may be small, making it impossible to form effective load balancing. Therefore, multiple ingress gateways can be grouped into a domain to share the load among them. In this case, weight generation and distribution need to be performed at the scheduling domain level. Optionally, the scheduling domain can be divided by geographical location, with nearby ingress gateways belonging to the same scheduling domain; or it can be divided by service deployment, with several ingress gateways deploying the same service belonging to the same scheduling domain.

[0094] Optionally, in this embodiment, a complete network view is formed by the controller: (ingress gateway, egress gateway, ingress gateway IP of computing power node, anycast IP, and computing power status information). Then, for each ingress gateway or each scheduling domain, the controller issues weight information (egress gateway, ingress gateway IP of computing power node, weight) corresponding to the anycast IP. After receiving a user request, the ingress gateway or scheduling domain can select computing power nodes according to the preset weight information, and then select the egress gateway. The path between the ingress gateway and the egress gateway remains BE.

[0095] In this embodiment, the network controller calculates the weights of computing nodes, generates a computing node weight table per ingress gateway / per advertisement domain, and sends it to the ingress gateway. The controller generates weight information and sends it to the ingress gateway or scheduling domain, reducing the computational and storage overhead of the router. At the same time, it avoids transmitting computing information in the routing system, reducing the burden on the routing system and enabling fast routing calculation.

[0096] Optionally, determining the weight information of computing nodes based on the computing network view further includes:

[0097] For each of the aforementioned entry gateways, determine whether the number of computing nodes for each type of service is greater than or equal to 2;

[0098] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the entry gateway;

[0099] If the number of computing power nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing power nodes;

[0100] or,

[0101] Generate the scheduling domain;

[0102] For each of the scheduling domains, determine whether the number of computing nodes for each type of service is greater than or equal to 2;

[0103] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the scheduling domain;

[0104] If the number of computing nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing nodes.

[0105] Optional, please refer to Figure 6Taking the ingress gateway as the granularity, the entire process includes: the controller forming a complete computing network view; generating an information table at the ingress gateway level; for each ingress gateway, if there are multiple computing nodes with the same anycast IP, generating weight information for each computing node based on the status information of the computing nodes; and the controller distributing weight information per anycast IP (egress gateway, computing node ingress gateway IP, weight); furthermore, if there is only one computing node for a certain ingress gateway and a certain anycast IP, then there is no need to generate and distribute weight information, thus reducing the amount of information distributed.

[0106] Optionally, at the scheduling domain level, the entire process includes: the controller forming a complete computing network view; the controller generating scheduling domains; optionally, scheduling domains can be divided by geographical location, with nearby ingress gateways belonging to the same scheduling domain; or they can be divided by service deployment, with several ingress gateways deploying the same service belonging to the same scheduling domain; generating information tables at the scheduling domain level; for each scheduling domain, if there are multiple computing power nodes with the same anycast IP, generating weight information for each computing power node based on the status information of the computing power nodes, and the controller distributing weight information per anycast IP (ingress gateway, egress gateway, computing power node ingress gateway IP, weight); if there is only one computing power node for a certain anycast IP within the scheduling domain, there is no need to generate and distribute weight information, thus reducing the amount of information distributed.

[0107] Optionally, when distributing weights, preset weight values ​​for computing nodes can be distributed through extended BGP / Network Configuration Protocol (Netconf) / Path Computation Element Communication Protocol (PCEP).

[0108] Taking the extended PCEP as an example, the controller initiates a path computation initiate (PCInitiate), which is actively sent by the path computation element (PCE) (handled by the controller) to the head node of the path computation client (PCC) (handled by the ingress gateway) to actively initialize the computing power node weight information (weight information generated by the controller).

[0109] It is worth noting that in this application Figure 5 and Figure 7 These are all examples, therefore the mapping relationships between some computing nodes and gateways have been omitted. Figure 7The example diagram shows the determination of weight information for each ingress gateway. Due to the lack of some mapping relationships, the determination of weight information is not solely based on the content of the current example diagram. For example, in the computing power routing ingress gateway IP2, the example diagram shows that only anycast3 is included, and anycast3 only includes computing power node ingress gateway IP5. However, the weight is not NA. In fact, this is because the example diagram omits other computing power node ingress gateways of anycast3 of computing power routing ingress gateway IP2. Therefore, the weight is displayed as 1. Similarly, the weights of other computing power node ingress gateways are also shown.

[0110] This application provides two refined weight distribution implementation methods, which can be applied to more scenarios, reduce the amount of information distributed, increase the transmission speed, and, in the case of only one computing node, there is no need to generate distribution weight information, which can further reduce the amount of information distributed.

[0111] Optionally, after sending the weight information of the computing power nodes to the ingress gateway or scheduling domain, the method further includes:

[0112] If the computing power node information or service deployment changes, determine whether it is necessary to regenerate and distribute the weight information of the computing power node, wherein the service deployment is associated with the computing power node information and the computing power node ingress gateway information connected to the egress gateway;

[0113] If it is necessary to regenerate and distribute the weights, the computing network view is regenerated based on the changed computing node information or service deployment, and the computing node ingress gateway information connected to the egress gateway.

[0114] Based on the regenerated computing network view, the weight information of the computing power nodes is regenerated and sent to the ingress gateway or scheduling domain.

[0115] Optionally, in some embodiments, when the status information of the computing power node changes or the service deployment changes, it is necessary to first determine whether the weight information of the computing power node needs to be regenerated and distributed. If so, the node weight needs to be updated through the Path Computation Update (PCupdate) message.

[0116] Specifically, this application provides some embodiments that require regenerating and distributing the weights. For example, when the status information of the computing power nodes reported by the cloud management system changes beyond a certain threshold, the controller will regenerate the weight information and trigger an update. When a new computing power node or a new anycast IP is deployed, if the new node meets the conditions for generating weight information in the above embodiments (for example, for each ingress gateway or each scheduling domain, the number of computing power nodes corresponding to the new service or the total number of computing power nodes after adding computing power nodes to the original service is greater than or equal to 2), then a new computing network view and the corresponding weight information of the computing power node will be regenerated and distributed.

[0117] This application also provides some embodiments that do not require regenerating and distributing the weight information of the computing power nodes. For example, if the change in the status information of the computing power nodes does not exceed a certain threshold, then no update is required. Another example is when a new service is added, and there is only one corresponding computing power node; therefore, it is not necessary to regenerate and distribute a new computing network view and the corresponding weight information of the computing power nodes.

[0118] It is worth noting that the above examples are only for illustrating the weight update conditions in the embodiments of this application, and the actual determination of whether to update the weight information is not limited to the above embodiments.

[0119] Please refer to Figure 8 This application also provides a method for computing power routing, including:

[0120] Step 21: Receive the weight information of the computing power nodes. The weight information is determined based on the computing network view, which includes the mapping relationship between the ingress gateway, the egress gateway, and the computing power node information.

[0121] Step 22: Based on the weight information, formulate a computing power routing decision.

[0122] In this embodiment, each ingress gateway or scheduling domain receives the weight information of computing power nodes. This weight information is determined based on a computing network view, which includes a mapping relationship between ingress gateways, egress gateways, and computing power node information. Based on the weight information, a computing power routing decision is made. In this embodiment, each ingress gateway or scheduling domain makes a computing power routing decision based on the weight information of the computing power nodes. The controller generates and distributes the weight information, reducing the computational and storage overhead of the router. Simultaneously, it avoids transmitting computing power information within the routing system, reducing the burden on the routing system and enabling rapid routing calculation.

[0123] Please refer to Figure 9 This application also provides a computing power routing system 30, comprising:

[0124] Data module 31 is used to collect information on the ingress gateway and computing node information of the computing power nodes connected to the egress gateway;

[0125] The computing network module 32 is used to determine a computing network view based on the collected information of the computing power nodes connected to the egress gateways and the computing power nodes. The computing network view includes the mapping relationship between the egress gateways, the egress gateways and the computing power nodes.

[0126] The computing network view is used to make computing power routing decisions.

[0127] Optionally, data module 31 includes:

[0128] The receiving module is used to receive the ingress gateway information of the computing node connected to the egress gateway. The ingress gateway information of the computing node includes at least: the egress gateway and the IP address of the computing node ingress gateway.

[0129] Receive computing power node information, which includes: the IP address of the computing power node's ingress gateway and the computing power node's status information.

[0130] Optionally, the computing power node entry gateway information may also include anycast address IP, wherein the anycast address IP is used to identify the same type of service;

[0131] The computing network view also includes the mapping relationship between the computing power node information and different services.

[0132] Optionally, the receiving module includes:

[0133] The transmission module is used to receive the ingress gateway information of the computing power node based on the extended distributed routing protocol;

[0134] The extended distributed routing protocol is an extended border gateway protocol link state protocol. The extended border gateway protocol link state protocol includes the path attribute of the extended border gateway protocol link state protocol. The path attribute is used to announce the topology information of the connected computing power nodes, and carries at least the ingress gateway IP of the computing power node.

[0135] Optionally, the computing power routing system 30 also includes:

[0136] The weight module is used to determine the weight information of computing power nodes based on the computing network view, and the weight information is used to formulate computing power routing decisions.

[0137] The weight information of the computing power nodes is sent to the ingress gateway or the scheduling domain, wherein the scheduling domain includes at least one ingress gateway.

[0138] Optionally, the weighting module also includes:

[0139] The first distribution module is used to determine, for each of the aforementioned entry gateways, whether the number of computing nodes for each type of service is greater than or equal to 2.

[0140] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the entry gateway;

[0141] If the number of computing power nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing power nodes;

[0142] or,

[0143] The second sending module is used to generate the scheduling domain;

[0144] For each of the scheduling domains, determine whether the number of computing nodes for each type of service is greater than or equal to 2;

[0145] If the number of computing power nodes corresponding to the service is greater than or equal to 2, generate the weight information of the computing power nodes for each type of service corresponding to the scheduling domain;

[0146] If the number of computing nodes corresponding to the service is less than 2, it is not necessary to determine the weight information of the computing nodes.

[0147] Optionally, the weight module may also include:

[0148] The update module is used to determine whether the weight information of the computing power node needs to be regenerated and distributed if the computing power node information or service deployment changes, wherein the service deployment is associated with the computing power node information and the computing power node ingress gateway information connected to the egress gateway.

[0149] If it is necessary to regenerate and distribute the weights, the computing network view is regenerated based on the changed computing node information or service deployment, and the computing node ingress gateway information connected to the egress gateway.

[0150] Based on the regenerated computing network view, the weight information of the computing power nodes is regenerated and sent to the ingress gateway or scheduling domain.

[0151] The computing power routing system provided in this application embodiment can achieve... Figure 4 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0152] This application provides an electronic device 40, see [link to relevant documentation] Figure 10 As shown, Figure 10This is a schematic block diagram of an electronic device 40 according to an embodiment of this application, including a processor 41, a memory 42, and a program or instructions stored in the memory 42 and executable on the processor 41. When the program or instructions are executed by the processor, they implement the steps in any of the computing power routing methods of this application.

[0153] This application provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements the various processes of the embodiments of the computing power routing method as described above and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0154] Computer-readable media include both permanent and non-permanent, removable and non-removable media, which can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0155] This application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above-described... Figure 1 Each process of the computing power routing method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0156] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0157] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a service classification device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0159] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A computing power routing method, characterized in that, The method comprises: collecting information of an entry gateway connected to an exit gateway of a computing power node and information of the computing power node; determining a computing network view according to the collected information of the entry gateway connected to the exit gateway of the computing power node and the information of the computing power node, the computing network view comprising a mapping relationship among information of an entry gateway, information of an exit gateway and information of a computing power node; wherein, the mapping from the exit gateway to the information of the computing power node is completed according to an IP of the entry gateway of the computing power node, and the mapping from the exit gateway to the information of the computing power node comprises a mapping from the exit gateway to the IP of the entry gateway of the computing power node to an anycast address IP to the information of the computing power node, and in combination with the mapping relationship between the entry gateway and the exit gateway, a computing network view comprising a complete mapping relationship from the entry gateway to the exit gateway to the information of the computing power node is formed; wherein, the computing network view is used to make a computing power routing decision.

2. The method of claim 1, wherein, The method comprises: receiving information of an entry gateway connected to an exit gateway of a computing power node, the information of the entry gateway connected to the exit gateway of the computing power node comprising at least the exit gateway and an IP of the entry gateway of the computing power node; receiving information of the computing power node, the information of the computing power node comprising the IP of the entry gateway of the computing power node and information of the computing power node.

3. The method of claim 2, wherein, The information of the entry gateway connected to the exit gateway of the computing power node further comprises an anycast address IP, wherein the anycast address IP is used to identify a same type of service; the computing network view further comprises a mapping relationship between the information of the computing power node and different services.

4. The method of claim 2, wherein, The method comprises: receiving the information of the entry gateway connected to the exit gateway of the computing power node based on an extended distributed routing protocol; wherein, the extended distributed routing protocol is an extended border gateway protocol link state protocol, the extended border gateway protocol link state protocol comprises a path attribute of the extended border gateway protocol link state protocol, and the path attribute is used to announce topology information of a computing power node and carries at least the IP of the entry gateway of the computing power node.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: determining weight information of the computing power node based on the computing network view, the weight information being used to make a computing power routing decision; downloading the weight information of the computing power node to an entry gateway or a scheduling domain, wherein the scheduling domain comprises at least one entry gateway.

6. The method of claim 5, wherein, The method further comprises: for each entry gateway, judging whether the number of computing power nodes of each type of service is greater than or equal to 2; if the number of computing power nodes corresponding to the service is greater than or equal to 2, generating weight information of the computing power nodes of each type of service corresponding to the entry gateway; if the number of computing power nodes corresponding to the service is less than 2, the weight information of the computing power nodes does not need to be determined; or, generating the scheduling domain; for each scheduling domain, judging whether the number of computing power nodes of each type of service is greater than or equal to 2; if the number of computing power nodes corresponding to the service is greater than or equal to 2, generating weight information of the computing power nodes of each type of service corresponding to the scheduling domain; if the number of computing power nodes corresponding to the service is less than 2, the weight information of the computing power nodes does not need to be determined.

7. The method of claim 5, wherein, The weight information of the computing power node is further issued to the entry gateway or the scheduling domain after the weight information of the computing power node is issued to the entry gateway or the scheduling domain. If the computing power node information or the service deployment changes, it is determined whether the weight information of the computing power node needs to be regenerated and issued, wherein the service deployment is associated with the computing power node information and the entry gateway information of the computing power node connected to the exit gateway. If the weight needs to be regenerated and issued, the computing power network view is regenerated based on the changed computing power node information or the service deployment and the entry gateway information of the computing power node connected to the exit gateway. The weight information of the computing power node is regenerated and issued to the entry gateway or the scheduling domain based on the regenerated computing power network view.

8. A hashpower routing system, comprising: It comprises: a data module for collecting entry gateway information of computing power nodes connected to the exit gateway and computing power node information; a computing power network module for determining a computing power network view according to the collected entry gateway information of computing power nodes connected to the exit gateway and computing power node information, wherein the computing power network view comprises a mapping relationship between the entry gateway, the exit gateway and the computing power node information; wherein the mapping from the exit gateway to the computing power node state information is completed according to the computing power node entry gateway IP, wherein the mapping from the exit gateway to the computing power node state information comprises a mapping from the exit gateway to the computing power node entry gateway IP to the anycast address IP to the computing power node state information, and the mapping relationship from the entry gateway to the exit gateway is combined to form a computing power network view comprising a complete mapping relationship from the entry gateway to the exit gateway to the computing power node state information; wherein the computing power network view is used to make computing power routing decisions.

9. An electronic device, comprising: It comprises: a processor, a memory and a program stored on the memory and executable on the processor, wherein the program is executed by the processor to realize the steps of the computing power routing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on a computer readable storage medium, wherein the computer program is executed by a processor to realize the steps of the computing power routing method according to any one of claims 1 to 7.

11. A computer program product, characterised in that, It comprises computer instructions, which are executed by a processor to realize the steps of the computing power routing method according to any one of claims 1 to 7.

Images