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

Abstract

The present invention provides a computing power-aware routing method, device, routing node and client device. The method comprises: obtaining a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service; according to the routing request, respectively calculating the network cost and computing cost of different paths corresponding to each destination node as the routing end point; according to the network cost and computing cost of different paths, determining the routing cost corresponding to different paths; according to the routing cost corresponding to different paths, determining the target path of the routing request. By adopting this method, the performance of different destination nodes is considered to affect the path calculation, and the computing cost is introduced, the network cost and computing cost are integrated, the network and computing joint path optimization is realized, and the routing cost of different paths is determined so as to obtain the optimal path.

Description

Technical Field

[0001] The present invention relates to the field of data communication network technology, and in particular to a computing power-aware routing method, device, routing node and client device. Background Art

[0002] At present, in IP bearer networks, in order to meet business needs, the forwarding path is calculated according to the bandwidth and delay requirements of the business. For example, the Constrained Shortest Path First (CSPF) algorithm is used to calculate the optimal forwarding path based on given constraints and network parameters, and generate the optimal path under the constraints. Its constraints may include cost, link attributes, bandwidth, etc.; the Cost is determined as follows: Cost = 100M / total bandwidth, and the path calculation is performed based on the above constraints. The CSPF algorithm is only used to calculate the end point of the Label Switching Path (LSP) tunnel, that is, to generate the best path to the designated router, that is, the destination router has been determined, and only the path to the destination router is selected.

[0003] In addition to the constraints, the metrics of existing path calculation algorithms are all based on network performance, such as network bandwidth, number of hops, remaining bandwidth and other parameters. The algorithm cost only considers the network cost and cannot guarantee the optimal performance of the destination node. The completion of the business requires not only guaranteeing the path in the network, but also ensuring the optimal performance of the destination node. Therefore, the existing routing method has the problem of not being able to obtain the "optimal path + optimal destination point". Summary of the invention

[0004] The technical solution of the present invention aims to provide a computing power-aware routing method, device, routing node and client device, which are used to solve the problem that the routing method using the prior art cannot obtain the optimal path.

[0005] An embodiment of the present invention provides a computing power-aware routing method, which is applied to a first routing node, wherein the method includes:

[0006] Obtaining a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0007] According to the routing request, respectively calculating the network cost and computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes;

[0008] Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths;

[0009] The target path of the routing request is determined according to the routing costs corresponding to different paths.

[0010] Optionally, in the routing method, the routing request further includes network requirement information and / or computing requirement information of the target service;

[0011] According to the routing request, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively, including:

[0012] According to the network demand information and / or the computing demand information, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively.

[0013] Optionally, the routing method, wherein determining the routing costs corresponding to different paths according to the network costs and computing costs of different paths, includes:

[0014] The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

[0015] Optionally, the routing method further comprises:

[0016] According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

[0017] Optionally, the routing method, wherein determining routing costs corresponding to different paths according to a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost, comprises:

[0018] The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

[0019] Optionally, the routing method, wherein determining the target path of the routing request according to routing costs corresponding to different paths, includes:

[0020] The path corresponding to the routing cost that meets the preset value is determined as the target path.

[0021] Optionally, in the routing method, the routing request includes at least two routing request information, which respectively include different destination nodes and network requirement information and computing requirement information requested by the corresponding destination nodes.

[0022] Optionally, in the routing method, in the routing request, the computing requirement information is recorded in an optional TLV field.

[0023] Optionally, in the routing method, the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand;

[0024] When determining the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

[0025] Optionally, the routing method further comprises:

[0026] Obtaining a path strategy of the generated path sent by the second routing node;

[0027] When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

[0028] Optionally, the routing method, wherein the second routing node recalculates the generated path, comprises:

[0029] When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost;

[0030] The generated path is recalculated according to the updated first weight value and the second weight value.

[0031] An embodiment of the present invention provides a computing power-aware routing method, which is applied to a client device, wherein the method includes:

[0032] Determine at least one destination node of the target service according to the node list sent by the domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0033] Sending a routing request; wherein the routing request includes at least one destination node of the requested target service.

[0034] Optionally, in the routing method, the routing request also includes network requirement information and computing requirement information.

[0035] Optionally, in the routing method, the routing request includes at least two routing request information, which respectively include different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

[0036] Optionally, in the routing method, in the routing request, the computing requirement information is recorded in an optional TLV field.

[0037] Optionally, in the routing method, the routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to network requirements and computing requirements.

[0038] An embodiment of the present invention further provides a routing node, comprising a transceiver and a processor, wherein:

[0039] The transceiver is used to obtain a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0040] The processor is used to calculate, according to the routing request, the network cost and the computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes;

[0041] Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths;

[0042] The target path of the routing request is determined according to the routing costs corresponding to different paths.

[0043] An embodiment of the present invention provides a client device, comprising a processor and a transceiver, wherein:

[0044] The processor is used to determine at least one destination node of the target service according to the node list sent by the domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0045] The transceiver is used to send a routing request;

[0046] The routing request includes at least one destination node of the requested target service.

[0047] An embodiment of the present invention provides a computing power-aware routing device, which is applied to a first routing node, wherein the device includes:

[0048] A request acquisition module, used to acquire a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0049] A first analysis module, used to calculate the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request;

[0050] The second analysis module is used to determine the routing costs corresponding to different paths according to the network costs and computing costs of different paths;

[0051] The third analysis module is used to determine the target path of the routing request according to the routing costs corresponding to different paths.

[0052] The embodiment of the present invention further provides a computing power-aware routing device, which is applied to a client device, wherein the device includes:

[0053] A determination module, configured to determine at least one destination node of a target service according to a node list sent by a domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0054] Request sending module, used to send routing requests,

[0055] The routing request includes at least one destination node of the requested target service.

[0056] An embodiment of the present invention provides a network device, which includes: 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-aware routing method as described in any one of the above items.

[0057] An embodiment of the present invention further provides a readable storage medium, wherein a program is stored on the readable storage medium, and when the program is executed by a processor, the steps in the computing power-aware routing method as described in any one of the above items are implemented.

[0058] At least one of the above technical solutions of the present invention has the following beneficial effects:

[0059] The computing power-aware routing method described in the embodiment of the present invention is adopted, based on a calculation algorithm that combines the destination node and the path, and a computing power parameter is added to the cost calculation to form a computing cost, realize joint decision-making of the network and the calculation, determine the routing costs corresponding to different paths, and thus determine the optimal target path, thereby solving the problem that the routing method using the prior art cannot obtain the optimal path. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of a flow chart of a routing method according to one embodiment of the present invention;

[0061] Figure 2 This is one of the system architecture diagrams using the routing method described in the embodiment of the present invention;

[0062] Figure 3 The second system architecture diagram adopting the routing method described in the embodiment of the present invention;

[0063] Figure 4 The third system architecture diagram adopting the routing method described in the embodiment of the present invention;

[0064] Figure 5 The fourth system architecture diagram adopting the routing method described in the embodiment of the present invention;

[0065] Figure 6 The fifth system architecture diagram using the routing method described in the embodiment of the present invention;

[0066] Figure 7 A schematic diagram of a flow chart of a routing method according to another embodiment of the present invention;

[0067] Figure 8 A schematic diagram of the structure of a routing node according to one embodiment of the present invention;

[0068] Fig. 9 A schematic diagram of the structure of a client device according to one embodiment of the present invention;

[0069] Fig.10 A schematic diagram of the structure of a routing device according to one embodiment of the present invention;

[0070] Fig.11 A schematic diagram of the structure of a routing device according to another embodiment of the present invention;

[0071] Fig.12 A schematic diagram of the structure of a network device according to one embodiment of the present invention;

[0072] Fig.13 A schematic diagram of the structure of a network device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0074] In order to solve the problem that the routing method using the existing technology cannot obtain the optimal path, the embodiment of the present invention provides a computing power-aware routing method, which takes into account the performance of different destination nodes affecting path calculation, introduces computing cost, integrates network cost and computing cost, realizes network and computing joint path optimization, and determines the routing costs of different paths so as to obtain the optimal path.

[0075] The computing power-aware routing method described in one embodiment of the present invention is applied to a first routing node, such as Figure 1 As shown, including:

[0076] S110, obtaining a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0077] S120, according to the routing request, respectively calculating the network cost and computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes;

[0078] S130, determining routing costs corresponding to different paths according to network costs and computing costs of different paths;

[0079] S140: Determine a target path of the routing request according to routing costs corresponding to different paths.

[0080] The computing power-aware routing method described in the embodiment of the present invention is adopted, based on a calculation algorithm that combines the destination node and the path, and a computing power parameter is added to the cost calculation to form a computing cost, realize the joint decision-making of the network and the calculation, determine the routing costs corresponding to different paths, and thus determine the optimal target path.

[0081] like Figure 2 As shown, a system structure diagram of the computing power-aware routing method according to an embodiment of the present invention is used, and the system includes a controller for implementing computing power scheduling and determining the destination node and transmission path for the terminal to initiate a service request. When the terminal initiates a service request, the controller (that is, the first routing node) generates a computing power scheduling strategy for the service on demand, and the computing power scheduling strategy includes determining the path and the destination node. Determining different transmission paths includes taking each destination node as the routing end point, determining each computing node through which the service initiated by the terminal is transmitted to the corresponding routing end point, and forming different transmission paths with paths of different computing nodes.

[0082] In the embodiment of the present invention, optionally, in step S110, the acquired routing request further includes network requirement information and / or computing requirement information of the target service;

[0083] In step S120, according to the routing request, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively, including:

[0084] According to the network demand information and / or the computing demand information, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively.

[0085] Wherein, in step S130, the routing costs corresponding to different paths are determined according to the network costs and computing costs of different paths, including:

[0086] The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

[0087] By adopting the routing method described in this embodiment, different network costs and computing cost weight values ​​are dynamically generated according to different service characteristics, that is, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost are determined. Taking the first weight value as w1 and the second weight value as w2 as an example, the calculation method of the routing cost W can be:

[0088] Path cost W = w1*network cost + w2*computation cost.

[0089] Optionally, the method further comprises:

[0090] According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

[0091] Optionally, the first routing node includes a weight definition functional unit for generating corresponding first weight values ​​and second weight values ​​based on the target service requested in the routing request, the business type determined by the target service, the current network status and the status of different computing power nodes.

[0092] With this implementation, the demand information of the target service in the routing request initiated by the client is mapped to network requirements, such as bandwidth and latency, through the weight definition functional unit; on the other hand, it is mapped to computing power requirements, such as demand information including service information, CPU and GPU, etc. Among them, with network requirements and computing power requirements as constraints, the network cost and computing cost of the corresponding different paths can be calculated respectively. And according to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, the first weight value of the corresponding network cost and the second weight value of the corresponding computing cost for different paths are determined.

[0093] Optionally, the first routing node also includes a path calculation functional unit, wherein the network requirements and computing requirements mapped according to the demand information of the target service and the above-mentioned first weight value and second weight value can be input into the path calculation functional unit, and the path calculation functional unit calculates the target node and the path based on the network requirements and computing requirements as constraints, combined with the first weight value and the second weight value.

[0094] Optionally, when determining the first weight value corresponding to the network cost and the second weight value corresponding to the computing cost, the weight decision can be assisted according to the proportion of service completion delay to achieve a joint decision of network cost and computing cost. For example, based on delay, services are divided into: network type, computing type and hybrid type. Services with small data volume, long distance, short computing time and relatively large transmission delay can be classified as network type; services with large data volume, short distance, long computing time and small transmission delay can be classified as computing type; services with similar delay, small data volume and short distance, or large data volume and long distance can be classified as hybrid type.

[0095] Optionally, by adopting the routing method described in the embodiment of the present invention, during the data packet forwarding process of the service, the first weight value and the second weight value can be dynamically adjusted according to the real-time network status and computing power resource status.

[0096] According to the above, in an embodiment of the present invention, determining the routing costs corresponding to different paths according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost includes:

[0097] The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

[0098] Optionally, in step S140, determining a target path of the routing request according to routing costs corresponding to different paths includes:

[0099] The path corresponding to the routing cost that meets the preset value is determined as the target path.

[0100] like Figure 3 As shown, when the terminal sends a routing request including a target service, the routing costs corresponding to different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of different paths, with the network requirement information and computing requirement information in the routing request as constraints, the target path of the routing request is determined according to the routing costs corresponding to the different paths, and the initial path information and the node information of each node are sent to the determined destination node and each computing node according to the determined target path.

[0101] Since the existing path calculation communication protocol must specify the destination node information to perform path calculation, in order to achieve the calculation of multiple destination nodes to obtain the optimal path, such as Figure 4As shown, the Domain Name Server (DNS) returns a node list including multiple destination nodes to the terminal, and the node list includes, for example, node 1, node 2, and node 3. Optionally, the node list includes the remaining computing power of each node.

[0102] In one implementation mode, optionally, the routing request information sent by the terminal to the controller (ie, the first routing node) includes different destination nodes and the network requirement information and computing requirement information requested by the destination nodes. Figure 4 As shown, the controller calculates the corresponding optimal paths based on different destination nodes. Specifically, the controller calculates the network cost cost and the computing cost cost based on the path corresponding to each destination node; optionally, the computing cost = computing power standard value / remaining computing power. Using the computing power-aware routing method described in the embodiment of the present invention, for the path corresponding to each destination node, the corresponding path cost is calculated based on the network cost, the computing cost, the first weight value w1 corresponding to the first network cost, and the second weight value w2 corresponding to the computing cost. That is, the path cost is calculated as follows: Path cost = f (network cost, computing cost, weight | condition: network demand, computing demand).

[0103] Using the above method, the controller compares the measurement values ​​of multiple "paths + nodes", i.e., the path cost, based on different weight values, determines the best path, and returns the path information of the determined best path to the terminal. Optionally, the path information may include the destination node and the information of each computing node from the terminal to the destination node. Optionally, the controller also returns the network cost cost, the calculation cost, the first weight value w1 corresponding to the first network cost, and the second weight value w2 corresponding to the calculation cost to the terminal. For example, Figure 4 As shown, the controller uses the above-mentioned calculation method to determine that node 1 is the destination node of the best path, and determines the best path from the terminal to node 1, and returns the corresponding path information to the terminal.

[0104] According to the above, in an embodiment of the present invention, optionally, the routing request sent by the client includes the requested destination node and the requested parameters; wherein the request parameters include network requirement information and / or computing requirement information of the target service, and the network requirement information and / or computing requirement information is used as a constraint condition during path calculation.

[0105] Based on the existing path computing element protocol (PCEP) extension, it includes a path computing client and a path computing server, wherein the path computing client (such as a terminal) sends the above routing request to the path computing server (such as one of the routing nodes).

[0106] Compared with the prior art, in the embodiment of the present invention, the routing request includes not only network requirement information but also computing requirement information.

[0107] Optionally, in the routing request, the calculation requirement information is recorded in an optional TLV field.

[0108] Further, optionally, the routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand;

[0109] When determining the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

[0110] In the embodiment of the present invention, optionally, a metric value object may be carried in the field T in the routing request to indicate the joint metric method. For example, by defining T=8, a joint metric method for calculating the path cost by using the network cost and the computing cost may be defined.

[0111] In the target path determined by the controller, when each computing node forwards the path strategy issued by the controller, due to the update of network and computing resources, the established strategy may not meet the business needs. Therefore, it is necessary to dynamically adjust the weight information of network / computing parameters and recalculate the path. Optionally, the recalculation can be performed by the intermediate routing node, that is, it can be performed by any routing node in the path process, such as an inter-domain router, which is used to recalculate the path between each domain; optionally, it can also be reported to the controller, and the controller will recalculate the path.

[0112] For example, Figure 5 For example, the target path for sending services from the terminal to the destination node initially set includes nodes 1, 2, 3 and 4. Among them, when node 2 predicts that the path delay through nodes 3 and 4 is greater than the expected transmission delay, and the proportion of the entire delay is higher, the weight information of node 2 can be used, such as increasing the weight of the corresponding network calculation cost, and recalculating the path, such as selecting the path as nodes 5 and 6 for sending services to achieve lower delay.

[0113] Of course, the above path recalculation can also be performed by a controller or a computing power management platform.

[0114] When the controller (such as the first routing node) performs path recalculation, optionally, the method further includes:

[0115] The first routing node obtains the path strategy of the generated path sent by the second routing node;

[0116] When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

[0117] Optionally, the second routing node recalculates the generated path, including:

[0118] When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost;

[0119] The generated path is recalculated according to the updated first weight value and the second weight value.

[0120] Therefore, in the embodiment of the present invention, optionally, when the network state and the computing state change, the network nodes on the path may initiate a dynamic adjustment of the local path, including: adjusting weight parameters based on the real-time network state and the computing state;

[0121] Specifically, Figure 6 As shown, network nodes that can implement path adjustment need to have the following functions:

[0122] Support weight definition function and run new path calculation algorithm. The computing power management platform issues weight definition strategy and new algorithm.

[0123] Supports the perception of business information and business demand information, such as business delay information, which can be issued by the controller;

[0124] Supports computing node status awareness, including computing node status update information, etc.

[0125] Compared with the path calculation algorithm that usually calculates the optimal route only based on the determined destination address, the routing method described in the embodiment of the present invention introduces the performance of the destination node as the calculation cost to calculate the path cost, and based on the business requirements, network parameters and calculation parameters, it can dynamically adjust the weight parameters of the network cost and the calculation cost to calculate the optimal path, so as to achieve the optimal path selection of the destination node and the path. Therefore, this method is adopted, combined with business requirements and network status and calculation status, and by dynamically setting the weight information of network cost and calculation cost, the utilization of network resources and computing resources can be optimized, and the business experience can be guaranteed; in addition, the forwarding path and destination node can be dynamically adjusted to increase the autonomy of the network node, and it can respond to and adjust the real-time network and computing status to meet the needs of the business.

[0126] Another aspect of the present invention is to provide a computing power-aware routing method, which is applied to a client device, such as Figure 7 As shown, the method includes:

[0127] S710, determining at least one destination node of a target service according to a node list sent by a domain name server DNS; wherein the node list records destination nodes corresponding to different target services;

[0128] S720, sending a routing request; wherein the routing request includes at least one destination node of the requested target service.

[0129] By adopting the computing power-aware routing method described in the embodiment of the present invention, the domain name server DNS sends at least one destination node to the client device, so that the routing request sent by the client device can include at least one destination node of the target service. In this way, the routing node (such as a controller) that receives the routing request can consider the performance of different destination nodes affecting the path calculation, and introduce computing costs, comprehensively integrate network costs and computing costs, realize network and computing joint path optimization, determine the routing costs of different paths, so as to obtain the optimal path.

[0130] Optionally, in the routing method, the routing request also includes network requirement information and computing requirement information.

[0131] Optionally, in the routing method, the routing request includes at least two routing request information, which respectively include different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

[0132] Optionally, in the routing method, in the routing request, the computing requirement information is recorded in an optional TLV field.

[0133] Optionally, in the routing method, the routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to network requirements and computing requirements.

[0134] The embodiment of the present invention also provides a routing node, such as Figure 8 As shown, it includes a transceiver 810 and a processor 820, wherein:

[0135] The transceiver 810 is used to obtain a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0136] The processor 820 is used to calculate, according to the routing request, the network cost and the computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes;

[0137] Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths;

[0138] The target path of the routing request is determined according to the routing costs corresponding to different paths.

[0139] Optionally, the routing node, wherein the routing request also includes network requirement information and / or computing requirement information of the target service;

[0140] The processor 820 calculates the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request, including:

[0141] According to the network demand information and / or the computing demand information, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively.

[0142] Optionally, in the routing node, the processor 820 determines the routing costs corresponding to different paths according to the network costs and computing costs of different paths, including:

[0143] The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

[0144] Optionally, in the routing node, the processor 820 is further configured to:

[0145] According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

[0146] Optionally, in the routing node, the processor 820 determines the routing costs corresponding to different paths according to the first weight value corresponding to the network cost and the second weight value corresponding to the computing cost, including:

[0147] The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

[0148] Optionally, in the routing node, the processor 820 determines the target path of the routing request according to routing costs corresponding to different paths, including:

[0149] The path corresponding to the routing cost that meets the preset value is determined as the target path.

[0150] Optionally, the routing node, wherein the routing request includes at least two routing request information, respectively including different destination nodes and network requirement information and computing requirement information requested by the corresponding destination nodes.

[0151] Optionally, in the routing node, the computing requirement information is recorded in an optional TLV field in the routing request.

[0152] Optionally, the routing node, wherein the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand;

[0153] When the processor 820 determines the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

[0154] Optionally, in the routing node, the processor 820 is further configured to:

[0155] Obtaining a path strategy of the generated path sent by the second routing node;

[0156] When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

[0157] Optionally, the routing node, wherein the second routing node recalculates the generated path, comprises:

[0158] When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost;

[0159] The generated path is recalculated according to the updated first weight value and the second weight value.

[0160] The embodiment of the present invention also provides a client device, such as Fig. 9 As shown, it includes a processor 910 and a transceiver 920, wherein:

[0161] The processor 910 is used to determine at least one destination node of a target service according to a node list sent by a domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0162] The transceiver 920 is used to send a routing request;

[0163] The routing request includes at least one destination node of the requested target service.

[0164] Optionally, in the client device, the routing request also includes network requirement information and computing requirement information.

[0165] Optionally, the client device, wherein the routing request includes at least two routing request information, respectively including different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

[0166] Optionally, in the client device, the computing requirement information is recorded in an optional TLV field in the routing request.

[0167] Optionally, in the client device, the routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to network requirements and computing requirements.

[0168] The embodiment of the present invention further provides a computing power-aware routing device, which is applied to a first routing node, such as Fig.10 As shown, the device comprises:

[0169] The request acquisition module 1001 is used to acquire a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0170] The first analysis module 1002 is used to calculate the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request;

[0171] The second analysis module 1003 is used to determine the routing costs corresponding to different paths according to the network costs and computing costs of different paths;

[0172] The third analysis module 1004 is used to determine the target path of the routing request according to the routing costs corresponding to different paths.

[0173] Optionally, in the routing device, the routing request further includes network requirement information and / or computing requirement information of the target service;

[0174] The first analysis module 1002 calculates the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request, including:

[0175] According to the network demand information and / or the computing demand information, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively.

[0176] Optionally, in the routing device, the third analysis module 1004 determines the routing costs corresponding to different paths according to the network costs and computing costs of different paths, including:

[0177] The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

[0178] Optionally, in the routing device, the second analysis module 1003 is further configured to:

[0179] According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

[0180] Optionally, in the routing device, the third analysis module 1004 determines the routing costs corresponding to different paths according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost, including:

[0181] The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

[0182] Optionally, in the routing device, the third analysis module 1004 determines the target path of the routing request according to the routing costs corresponding to different paths, including:

[0183] The path corresponding to the routing cost that meets the preset value is determined as the target path.

[0184] Optionally, in the routing device, the routing request includes at least two routing request information, which respectively include different destination nodes and network requirement information and computing requirement information requested by the corresponding destination nodes.

[0185] Optionally, in the routing device, the computing requirement information is recorded in an optional TLV field in the routing request.

[0186] Optionally, in the routing device, the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand;

[0187] When determining the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

[0188] Optionally, the routing device further comprises a fourth analysis module 1005, configured to:

[0189] Obtaining a path strategy of the generated path sent by the second routing node;

[0190] When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

[0191] Optionally, in the routing device, the second routing node recalculates the generated path, comprising:

[0192] When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost;

[0193] The generated path is recalculated according to the updated first weight value and the second weight value.

[0194] The embodiment of the present invention also provides a computing power-aware routing device, which is applied to a client device, such as Fig.11 As shown, the device comprises:

[0195] A determination module 1101 is used to determine at least one destination node of a target service according to a node list sent by a domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0196] The request sending module 1102 is used to send a routing request.

[0197] The routing request includes at least one destination node of the requested target service.

[0198] Optionally, in the routing device, the routing request also includes network requirement information and computing requirement information.

[0199] Optionally, in the routing device, the routing request includes at least two routing request information, which respectively include different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

[0200] Optionally, in the routing device, the computing requirement information is recorded in an optional TLV field in the routing request.

[0201] Optionally, in the routing device, the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to network requirements and computing requirements.

[0202] Another aspect of the present invention provides a network device, wherein the network device is a routing node, such as Fig.12 As shown, the base station includes: a processor 1201; and a memory 1203 connected to the processor 1201 via a bus interface 1202, the memory 1203 is used to store programs and data used by the processor 1201 when performing operations, and the processor 1201 calls and executes the programs and data stored in the memory 1203.

[0203] The transceiver 1204 is connected to the bus interface 1202 and is used to receive and send data under the control of the processor 1201. Specifically, the processor 1201 is used to read the program in the memory 1203 and execute the following process:

[0204] Obtaining a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service;

[0205] According to the routing request, respectively calculating the network cost and computing cost of different paths corresponding to each destination node as the routing end point;

[0206] Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths;

[0207] The target path of the routing request is determined according to the routing costs corresponding to different paths.

[0208] Optionally, the network device, wherein the routing request also includes network requirement information and / or computing requirement information of the target service;

[0209] The processor 1201 calculates the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request, including:

[0210] According to the network demand information and / or the computing demand information, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively.

[0211] Optionally, in the network device, the processor 1201 determines the routing costs corresponding to different paths according to the network costs and computing costs of different paths, including:

[0212] The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

[0213] Optionally, in the network device, the processor 1201 is further configured to:

[0214] According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

[0215] Optionally, in the network device, the processor 1201 determines the routing costs corresponding to different paths according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost, including:

[0216] The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

[0217] Optionally, in the network device, the processor 1201 determines the target path of the routing request according to routing costs corresponding to different paths, including:

[0218] The path corresponding to the routing cost that meets the preset value is determined as the target path.

[0219] Optionally, the network device, wherein the routing request includes at least two routing request information, respectively including different destination nodes and network requirement information and computing requirement information requested by the corresponding destination nodes.

[0220] Optionally, in the network device, the computing requirement information is recorded in an optional TLV field in the routing request.

[0221] Optionally, the network device, wherein the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand;

[0222] When the processor 1201 determines the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

[0223] Optionally, in the network device, the processor 1201 is further configured to:

[0224] Obtaining a path strategy of the generated path sent by the second routing node;

[0225] When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

[0226] Optionally, in the network device, the second routing node recalculates the generated path, comprising:

[0227] When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost;

[0228] The generated path is recalculated according to the updated first weight value and the second weight value.

[0229] Among them, Fig.12 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 1201 and memory represented by memory 1203. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1204 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 1201 is responsible for managing the bus architecture and general processing, and the memory 1203 may store data used by the processor 1201 when performing operations.

[0230] One embodiment of the present invention further provides a terminal, such as Fig.13As shown, the terminal includes: a processor 1301; and a memory 1303 connected to the processor 1301 via a bus interface 1302, wherein the memory 1303 is used to store programs and data used by the processor 1301 when performing operations, and a transceiver 1304 is connected to the bus interface 1302, and is used to receive and send data under the control of the processor 1301.

[0231] in,

[0232] When the processor 1301 calls and executes the program and data stored in the memory 1303, the following process is performed:

[0233] Determine at least one destination node of the target service according to the node list sent by the domain name server DNS; wherein the node list records the destination nodes corresponding to different target services;

[0234] Sending a routing request; wherein the routing request includes at least one destination node of the requested target service.

[0235] Optionally, in the terminal, the routing request also includes network requirement information and computing requirement information.

[0236] Optionally, in the terminal, the routing request includes at least two routing request information, respectively including different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

[0237] Optionally, in the terminal, in the routing request, the computing requirement information is recorded in an optional TLV field.

[0238] Optionally, in the terminal, the routing request further includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to network requirements and computing requirements.

[0239] It should be noted that in Fig.13In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1301 and various circuits of memory represented by memory 1303 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1304 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. For different terminals, the user interface 1305 may also be an interface capable of externally connecting or internally connecting required devices, and the connected devices include but are not limited to a keypad, a display, a speaker, a microphone, a joystick, and the like. The processor 1301 is responsible for managing the bus architecture and general processing, and the memory 1303 may store data used by the processor 1301 when performing operations.

[0240] In addition, a specific embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps in the computing power-aware routing method as described above are implemented.

[0241] Specifically, the computer-readable storage medium is applied to the above-mentioned routing node or client device. When applied to the routing node and the client device respectively, the execution steps in the corresponding routing method are described in detail above and will not be repeated here.

[0242] In the several embodiments provided in the present 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0243] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0244] 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, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0245] The above is a preferred embodiment of the present invention. 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 of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A computing power-aware routing method, applied to a first routing node, characterized in that: The method comprises: Obtaining a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service; According to the routing request, respectively calculating the network cost and computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes; Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths; Determining a target path of the routing request according to routing costs corresponding to different paths; The routing request also includes network requirement information and / or computing requirement information of the target service; According to the routing request, the network cost and computing cost of different paths corresponding to each destination node as the routing end point are calculated respectively, including: Using the network demand information and / or the computing demand information as constraints, respectively calculating the network costs of different paths corresponding to each destination node as the routing end point; and, The network requirement information and / or the computing requirement information are used as constraint conditions to respectively calculate the computing costs of different paths corresponding to each destination node as the routing end point.

2. The routing method according to claim 1, characterized in that: Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths, including: The routing costs corresponding to different paths are determined according to the first weight value corresponding to the network cost and the second weight value corresponding to the calculation cost.

3. The routing method according to claim 2, characterized in that: The method further comprises: According to the target service, the business type determined by the target service, the current network status and the status of different computing nodes, a first weight value corresponding to the network cost and a second weight value corresponding to the computing cost for different paths are determined.

4. The routing method according to claim 2, characterized in that: Determining routing costs corresponding to different paths according to a first weight value corresponding to the network cost and a second weight value corresponding to the calculation cost includes: The routing costs corresponding to the different paths are determined according to the network costs, computing costs, first weight values ​​and second weight values ​​of the different paths, with the network requirement information and computing requirement information in the routing request as constraints.

5. The routing method according to claim 1, characterized in that: Determining a target path of the routing request according to routing costs corresponding to different paths includes: The path corresponding to the routing cost that meets the preset value is determined as the target path.

6. The routing method according to claim 1, characterized in that: The routing request includes at least two routing request information, which respectively include different destination nodes and network requirement information and computing requirement information requested by the destination nodes.

7. The routing method according to claim 1 or 6, characterized in that: In the routing request, the computing requirement information is recorded in an optional TLV field.

8. The routing method according to claim 1, characterized in that: The routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand; When determining the routing costs corresponding to different paths according to the network costs and computing costs of different paths, the routing costs are calculated in a joint metric manner indicated by the preset indication field according to the network costs and computing costs of the different paths.

9. The routing method according to claim 1, characterized in that: The method further comprises: Obtaining a path strategy of the generated path sent by the second routing node; When it is determined that the current network status and / or computing resources do not satisfy the path strategy, the generated path is recalculated, or update information is reported to the second routing node, and the second routing node recalculates the generated path.

10. The routing method according to claim 9, characterized in that: The second routing node recalculates the generated path, including: When updating the path strategy generation, the first weight value corresponding to the network cost and / or the second weight value corresponding to the computing cost; The generated path is recalculated according to the updated first weight value and the second weight value.

11. A computing power-aware routing method, applied to a client device, characterized in that: The method comprises: Determine at least one destination node of the target service according to the node list sent by the domain name server DNS; wherein the node list records the destination nodes corresponding to different target services; Sending a routing request; wherein the routing request includes at least one destination node of the requested target service; The routing request also includes network requirement information and / or computing requirement information; the network requirement information and / or computing requirement information are used as constraints to calculate the network cost of different paths corresponding to each destination node as the routing end point, and to calculate the computing cost of different paths corresponding to each destination node as the routing end point.

12. The routing method according to claim 11, characterized in that: The routing request includes at least two routing request information, which respectively include different target nodes and network requirement information and computing requirement information requested by the corresponding target nodes.

13. The routing method according to claim 11 or 12, characterized in that: In the routing request, the computing requirement information is recorded in an optional TLV field.

14. The routing method according to claim 11, characterized in that: The routing request also includes a preset indication field for indicating a joint measurement method for calculating the routing cost according to the network demand and the computing demand.

15. A routing node, characterized in that: It includes a transceiver and a processor, wherein: The transceiver is used to obtain a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service; The processor is used to calculate, according to the routing request, the network cost and the computing cost of different paths corresponding to each destination node as the routing end point; wherein the different paths include different network paths and / or different destination nodes; Determine the routing costs corresponding to different paths based on the network costs and computing costs of different paths; Determining a target path of the routing request according to routing costs corresponding to different paths; The routing request also includes network requirement information and / or computing requirement information of the target service; The processor calculates the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request, including: Using the network demand information and / or the computing demand information as constraints, respectively calculating the network costs of different paths corresponding to each destination node as the routing end point; and, The network requirement information and / or the computing requirement information are used as constraint conditions to respectively calculate the computing costs of different paths corresponding to each destination node as the routing end point.

16. A client device, characterized in that: It includes a processor and a transceiver, wherein: The processor is used to determine at least one destination node of the target service according to the node list sent by the domain name server DNS; wherein the node list records the destination nodes corresponding to different target services; The transceiver is used to send a routing request; Wherein, the routing request includes at least one destination node of the requested target service; The routing request also includes network requirement information and / or computing requirement information; the network requirement information and / or computing requirement information are used as constraints to calculate the network cost of different paths corresponding to each destination node as the routing end point, and to calculate the computing cost of different paths corresponding to each destination node as the routing end point.

17. A computing power-aware routing device, applied to a first routing node, characterized in that: The device comprises: A request acquisition module, used to acquire a routing request sent by a client; wherein the routing request includes at least one destination node of the requested target service; A first analysis module, used to calculate the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request; The second analysis module is used to determine the routing costs corresponding to different paths according to the network costs and computing costs of different paths; A third analysis module, used to determine the target path of the routing request according to the routing costs corresponding to different paths; The routing request also includes network requirement information and / or computing requirement information of the target service; The first analysis module calculates the network cost and computing cost of different paths corresponding to each destination node as the routing end point according to the routing request, including: Using the network demand information and / or the computing demand information as constraints, respectively calculating the network costs of different paths corresponding to each destination node as the routing end point; and, The network requirement information and / or the computing requirement information are used as constraint conditions to respectively calculate the computing costs of different paths corresponding to each destination node as the routing end point.

18. A computing power-aware routing device, applied to a client device, characterized in that: The device comprises: A determination module, configured to determine at least one destination node of a target service according to a node list sent by a domain name server DNS; wherein the node list records the destination nodes corresponding to different target services; Request sending module, used to send routing requests, Wherein, the routing request includes at least one destination node of the requested target service; The routing request also includes network requirement information and / or computing requirement information; the network requirement information and / or computing requirement information are used as constraints to calculate the network cost of different paths corresponding to each destination node as the routing end point, and to calculate the computing cost of different paths corresponding to each destination node as the routing end point.

19. A network device, characterized in that: include: 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-aware routing method as described in any one of claims 1 to 10 is implemented, or the computing power-aware routing method as described in any one of claims 11 to 14 is implemented.

20. A readable storage medium, characterized in that: The readable storage medium stores a program, and when the program is executed by the processor, it implements the steps in the computing power-aware routing method as described in any one of claims 1 to 10, or implements the steps in the computing power-aware routing method as described in any one of claims 11 to 14.

Images