Routing method, architecture, device, storage medium and product

Abstract

The invention relates to the technical field of computing power routing, in particular to a routing method, architecture, equipment, a storage medium and a product, and discloses a routing method which comprises the following steps: a computing power management and control center node sends a segment identifier list of computing power service to a computing power request node; and the computing power routing node receives the computing power service request flow from the computing power request node and performs computing power routing scheduling based on the computing power service identifier so as to meet the computing network end-to-end service of the user and improve the processing efficiency of the computing power service demand of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of computing power routing, and particularly to a routing method, architecture, device, storage medium and product. Background Art

[0002] Currently, IPv6 and the service function chain based on IPv6 cannot meet the end-to-end service of computing network, and the processing efficiency of the computing power service requirements of users is relatively low.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main object of the present invention is to provide a routing method, architecture, device, storage medium and product, aiming to solve the technical problem that currently IPv6 and the service function chain based on IPv6 cannot meet the end-to-end service of computing network, and the processing efficiency of the computing power service requirements of users is relatively low.

[0005] To achieve the above object, the present invention provides a routing method, which is applied to a computing power routing node, and the method includes the following steps:

[0006] Receive the computing power service request traffic from a computing power request node, where at least one computing power service identifier is carried in the computing power service request traffic, and the computing power service identifier is sent by a computing power management and control center node to the computing power request node;

[0007] Perform computing power routing scheduling based on the computing power service identifier.

[0008] Optionally, the performing computing power routing scheduling based on the computing power service identifier includes:

[0009] Generate a computing power routing path based on the computing power service identifier;

[0010] Perform computing power routing scheduling according to the computing power routing path.

[0011] Optionally, the generating a computing power routing path based on the computing power service identifier includes:

[0012] Analyze the computing power service identifier to obtain a computing power routing path;

[0013] And / or

[0014] Receive the computing power routing path issued by the computing power management and control center node, where the computing power routing path is arranged by the computing power management and control center node based on the computing power service identifier.

[0015] Optionally, the analyzing the computing power service identifier to obtain a computing power routing path includes:

[0016] Parse the computing power service identifier to obtain a target field for characterizing the public address of the computing power routing node;

[0017] When the target field meets the first forwarding condition, query the computing power routing path corresponding to the computing power service identifier through the computing power forwarding table.

[0018] Optionally, the method includes at least one of the following:

[0019] The computing power forwarding table records the mapping relationship between each computing power routing node in the SRv6 computing power routing architecture;

[0020] The SRv6 computing power routing architecture is composed of a computing power request node, a computing power resource node, a computing power management and control center node, and at least one computing power routing node;

[0021] The first forwarding condition includes: the computing power routing node where the computing power service identifier is currently located is the same as the computing power routing node corresponding to the public address recorded in the target field.

[0022] Optionally, the querying the computing power routing path corresponding to the computing power service identifier through the computing power forwarding table includes:

[0023] Query the next-hop computing power routing node and the outgoing interface corresponding to the computing power service identifier through the computing power forwarding table. The next-hop computing power routing node is the computing power routing node that receives the computing power service identifier next in the computing power routing path, and the outgoing interface is used to send the computing power service identifier from the currently located computing power routing node to the next-hop computing power routing node.

[0024] Optionally, the performing computing power routing scheduling according to the computing power routing path includes:

[0025] Guide the flow direction of the computing power service data packet carried in the computing power service request traffic based on the computing power routing path.

[0026] Optionally, the guiding the flow direction of the computing power service data packet carried in the computing power service request traffic based on the computing power routing path includes:

[0027] Send the computing power service data packet to the next-hop computing power routing node through the outgoing interface.

[0028] Optionally, the sending the computing power service data packet to the next-hop computing power routing node through the outgoing interface includes:

[0029] Update the computing power service data packet;

[0030] Send the updated computing power service data packet to the next-hop computing power routing node through the forwarding interface.

[0031] Optionally, updating the computing power service data packet includes at least one of the following methods:

[0032] Remove the computing power service identifier and the external SRv6 encapsulation information from the computing power service data packet;

[0033] Retain the computing power service identifier and the external SRv6 encapsulation information in the computing power service data packet;

[0034] Retain the computing power service identifier in the computing power service data packet and remove the external SRv6 encapsulation information.

[0035] Optionally, the external SRv6 encapsulation information is used to encapsulate the routing extension header in the computing power service request traffic. The routing extension header is a message in the computing power service request traffic used to represent at least one computing power service identifier. The at least one computing power service identifier is respectively used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources for the computing power request node.

[0036] Optionally, the method further includes:

[0037] Sense computing power resource information;

[0038] The computing power resource information includes at least one of the following at least:

[0039] Computing power information used to represent the attributes, status, and / or performance of the computing power resource device;

[0040] Network information used to represent the topology, link attributes, and / or SRv6 routing policies of each computing power routing node in the computing power scheduling device.

[0041] Optionally, sensing the computing power resource information includes:

[0042] When the SRv6 computing power routing architecture is a distributed computing power routing architecture or a hybrid computing power routing architecture, sense the computing power resource information.

[0043] Optionally, the method further includes:

[0044] Send computing power announcement information.

[0045] Optionally, the computing power announcement information includes at least:

[0046] Extended SRv6 computing power service TLV message.

[0047] Optionally, the method includes at least one of the following at least:

[0048] The extended SRv6 computing power service TLV packet carries an SRv6 computing power service identifier;

[0049] The extended SRv6 computing power service TLV packet is defined according to the target routing advertisement protocol corresponding to the SRv6 computing power routing architecture;

[0050] The SRv6 computing power routing architecture is a centralized computing power routing architecture, a distributed computing power routing architecture, or a hybrid computing power routing architecture;

[0051] The target routing advertisement protocol at least includes an interior gateway protocol, a border gateway protocol, and / or a border gateway - link state protocol.

[0052] Optionally, the extended SRv6 computing power service TLV packet under the border gateway protocol at least includes at least one of the following:

[0053] TLV type field;

[0054] TLV length field;

[0055] Reserved field;

[0056] At least one first TLV field of the SRv6 computing power service.

[0057] Optionally, when the TLV type field is a preset type, at least one first TLV field of the SRv6 computing power service carries an SRv6 computing power service calculation TLV field, and the SRv6 computing power service calculation TLV field carries a computing power service identifier.

[0058] Optionally, the SRv6 computing power service calculation TLV field at least includes at least one of the following:

[0059] First type field of the first TLV;

[0060] Length field of the first TLV;

[0061] First reserved field;

[0062] Numeric field of the SRv6 computing power service identifier;

[0063] Control identifier field of the computing power service identifier;

[0064] Interface behavior field of the SRv6 computing power service identifier;

[0065] Second reserved field;

[0066] At least one second TLV field of the SRv6 computing power service data.

[0067] Optionally, at least one second TLV field of the SRv6 computing power service data includes at least one of the following:

[0068] The first type field of the second TLV;

[0069] The second TLV length field;

[0070] The first position identifier length field;

[0071] The second position identifier length field;

[0072] The function identifier length field;

[0073] The variable identifier length field;

[0074] The conversion character length field;

[0075] The conversion offset field.

[0076] Optionally, the extended SRv6 computing power service TLV message under the interior gateway protocol includes at least:

[0077] The type field, length field, control identifier field, SRv6 interface function field, computing power service identifier field, the length field of the second TLV, and at least one of the at least one second TLV field;

[0078] Or

[0079] The type field, length field, control identifier field, reserved field, interaction interface identifier field, computing power service identifier field, and at least one of the at least one second TLV field.

[0080] Optionally, the extended SRv6 computing power service TLV under the border gateway - connection state protocol further includes: the SRv6 computing power service information TLV message and the SRv6 interface function TLV message;

[0081] Wherein, the SRv6 computing power service information TLV message includes at least one of the type field, length field, and computing power service identifier field;

[0082] The SRv6 interface function TLV message includes at least one of the type field, length field, SRv6 interface function identifier field, control identifier field, and algorithm identifier field.

[0083] The present invention provides a routing method, which is applied to a computing power management and control center node, and the method includes the following steps:

[0084] Send a segment identifier list of the computing power service to the computing power request node, where the segment identifier list includes at least one computing power service identifier.

[0085] Optionally, each of the at least one computing power service identifier is used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources to the computing power request node.

[0086] Optionally, the routing method further includes:

[0087] Sense computing power resource information;

[0088] Generate a segment identifier list carrying at least one computing power service identifier based on the computing power resource information.

[0089] Optionally, the sensing of the computing power resource information includes:

[0090] When the SRv6 computing power routing architecture is a centralized computing power routing architecture or a hybrid computing power routing architecture, sense the computing power resource information, and the SRv6 computing power routing system is composed of a computing power request node, a computing power resource node, a computing power management and control center node, and / or at least one computing power routing node.

[0091] Optionally, the sensing of the computing power resource information includes:

[0092] Obtain the computing power resource information through the computing power management and control center node based on at least one of the Interior Gateway Protocol, the Border Gateway Protocol, and the Border Gateway - Connection State Protocol;

[0093] And / or

[0094] Obtain the computing power resource information through the computing power management and control center node based on the new computing network integrated advertisement protocol.

[0095] Optionally, the computing power resource information includes at least one of the following at least:

[0096] Computing power information used to characterize the attributes, status, and / or performance of the computing power resource device;

[0097] Network information used to characterize the topology, link attributes, and / or SRv6 Policy policies of each computing power routing node in the computing power scheduling device;

[0098] The computing power information is obtained through at least one of the Interior Gateway Protocol, the Border Gateway Protocol, the RESTful interface, and the distributed database:

[0099] The network information is obtained through the Border Gateway - Connection State Protocol and / or Telemetry.

[0100] Optionally, the generating of the segment identifier list carrying at least one computing power service identifier based on the computing power resource information includes:

[0101] Create a computing power service identifier;

[0102] Associate the computing power service identifier with the computing power resource information to obtain at least one computing power service identifier for identifying at least one computing power service instance;

[0103] Generate a segment identifier list of the computing power service according to the at least one computing power service identifier.

[0104] Optionally, the method further includes:

[0105] Send a computing power routing path to a computing power routing node, for instructing the computing power routing node to perform computing power routing scheduling or guiding the flow direction of computing power service request traffic.

[0106] Optionally, the computing power service request traffic is sent from a computing power request node to the computing power routing node.

[0107] Optionally, before sending the computing power routing path to the computing power routing node, it further includes:

[0108] Based on a user service computing power request, orchestrate a computing power service identifier to generate a computing power routing path, where the user service computing power request is sent by a computing power request node and is used to characterize the computing power load of the computing power request node.

[0109] The present invention provides a routing method, which is applied to a computing power request node, and the method includes the following steps:

[0110] Send computing power service request traffic to a computing power routing node, where at least one computing power service identifier is carried in the computing power service request traffic.

[0111] Optionally, before sending the computing power service request traffic to the computing power routing node, it further includes:

[0112] Generate computing power service request traffic according to a segment identifier list of the computing power service, where the segment identifier list of the computing power service is sent by a computing power management center node.

[0113] Optionally, the segment identifier list includes at least one computing power service identifier, and the at least one computing power service identifier is respectively used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power service or computing power resources for the computing power request node.

[0114] Optionally, before generating the computing power service request traffic according to the segment identifier list of the computing power service, it further includes:

[0115] Send a user service computing power request to a computing power management center node, for requesting the computing power management center node to issue a computing power service identifier.

[0116] In addition, to achieve the above object, the present invention further provides a routing device, which includes: a memory, a processor, and a routing program stored on the memory and executable on the processor, and the routing program is configured to implement the steps of the routing method as described above.

[0117] In addition, to achieve the above object, the present invention further provides a storage medium, on which a routing program is stored, and when the routing program is executed by a processor, it implements the steps of the routing method as described above.

[0118] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the routing method as described above.

[0119] One or more technical solutions proposed by the present invention have at least the following technical effects: The present invention discloses a routing method, which includes: a computing power management and control center node sends a segment identifier list of computing power services to a computing power request node; a computing power routing node receives the computing power service request traffic from the computing power request node, and performs computing power routing scheduling based on the computing power service identifier to meet the user's end-to-end computing network service and improve the processing efficiency of the user's computing power service requirements. Description of the Drawings

[0120] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0121] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0122] Figure 1 It is a schematic flowchart of the first embodiment of the routing method of the present invention;

[0123] Figure 2 It is a schematic diagram of the SRv6 computing power routing system architecture of an embodiment of the routing method of the present invention;

[0124] Figure 3 It is a schematic diagram of the architecture of the SRv6 computing power routing control plane of an embodiment of the routing method of the present invention;

[0125] Figure 4 It is a schematic diagram of the networking architecture of the SRv6 computing power routing system of an embodiment of the routing method of the present invention;

[0126] Figure 5Schematic diagram of the computing power routing scenario of a distributed multi-computing power instance in an embodiment of the routing method of the present invention;

[0127] Figure 6 Schematic diagram of the service chain scenario supported under the SRv6 network architecture in an embodiment of the routing method of the present invention;

[0128] Figure 7 Flow chart of the second embodiment of the routing method of the present invention;

[0129] Figure 8 Flow chart of the third embodiment of the routing method of the present invention;

[0130] Figure 9 Schematic diagram of the structure of the routing device in the hardware operating environment involved in the embodiment solution of the present invention.

[0131] The implementation, functional features, and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0132] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0133] For a better understanding of the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0134] Based on this, an embodiment of the present invention provides a routing method, referring to Figure 1 , Figure 1 Flow chart of the first embodiment of a routing method of the present invention.

[0135] In this embodiment, the routing method is applied to a computing power routing node, and the routing method includes:

[0136] Step S10: Receive the computing power service request traffic from the computing power request node.

[0137] It should be noted that the execution subject of this embodiment can be a programmable forwarding device supporting SRv6, a routing device that realizes functions such as computing power-aware routing decision-making, such as a routing server or a routing cabinet, etc., or other routing devices that can realize the above functions. This embodiment does not make specific limitations on this.

[0138] It should be understood that computing power routing dynamically selects the "forwarding path + destination service node" that meets service requirements through the perception of service requirements, computing power resources, and network resources, realizing the deep integration of computing power and network in dimensions such as transaction, operation, scheduling, orchestration, and forwarding. In order to perceive changes in the computing power status of edge nodes or cloud nodes, changes in the resource status of network nodes, and changes in the traffic model, a new type of computing power routing technology that unifies computing power resources and IP topology routing is required to achieve resource scheduling and computing power forwarding in the network domain and meet the service requirements of the computing power network.

[0139] As an innovative technology application based on IPv6, IPv6 data plane segment routing (SR over IPv6, SRv6) has the advantages of high network programmability and strong scalability. SRv6 can achieve a three-layer programmable space through flexible segment identifier sequence arrangement, flexible segment identifier field arrangement, and flexible combination of Type Length Value (TLV), more flexibly meet the requirements of new computing power network services, expand and enhance the network bearing capacity of SRv6, and be compatible with IPv6, making it easier to promote the implementation of computing power-network integration in the industry.

[0140] Due to the diversity and hierarchical granularity of computing power resources and services, such as IaaS, PaaS, etc., as well as their special features in deployment mode (such as distributed multi-instances), status mode, and impact on IP routing, currently SRv6 and SFC based on SRv6 cannot meet the end-to-end services of computing power-network. It is necessary to expand and enhance the forwarding plane and control plane based on SRv6 according to the characteristics of computing power resources and services, and standardize the computing power routing based on SRv6 to enable future computing power-network integration services.

[0141] The SRv6 computing power routing architecture is as Figure 2 shown, consisting of a flexible and comprehensive SRv6 management plane, an intelligent perception SRv6 control plane, and a function-enhanced SRv6 forwarding plane. Among them, the control plane supports perceiving and advertising computing power service information, performing calculations through SRv6 function programming and maintaining computing power routing information, and generating SRv6-based computing power routing and routing policies; the forwarding plane supports scheduling service traffic to the "optimal" service instance through the network path based on the computing power service identifier, supports end-to-end service routing of computing power-network and SFC routing based on computing power services; the management plane supports perceiving and constructing a computing power-network resource view, responsible for monitoring, configuring, and maintaining the computing power network and computing power routing, and realizing end-to-end service quality detection for applications.

[0142] Refer to Figure 3 , Figure 3This is a schematic diagram of the architecture of the SRv6 computing power routing control plane of this embodiment. The computing power routing control plane based on SRv6 introduces computing power information into the routing domain, combines the SRv6 capabilities and information of the computing power routing nodes, calculates and arranges forwarding paths that meet the computing power service requirements, and performs computing power-aware routing control and scheduling. The SRv6-based computing power routing control plane process mainly includes computing power service perception, computing power service notification, computing power service programming, and computing power routing control.

[0143] It should be noted that the reference Figure 4 , Figure 4 This is a schematic diagram of the networking architecture of the SRv6 computing power routing system in this embodiment. The routing architecture includes at least: a computing power request node, a computing power control center node, and at least one computing power routing node. In addition, the routing architecture also includes a computing power node for providing computing power resources. The computing power request node is connected to at least one computing power routing node (computing power entry routing node), and the computing power node is connected to at least one computing power routing node (computing power exit routing node). The computing power control center node is respectively connected to the computing power request node, the computing power node, and at least one computing power routing node. The computing power request node refers to a terminal device or service node that initiates computing power resource demand at the edge of the network. The computing power service request traffic carries at least one computing power service identifier, and the computing power service identifier is sent by the computing power control center node to the computing power request node; the computing power control center node is mainly used as a core node for global resource scheduling to achieve joint optimization of computing network resources; the computing power routing node supports programmable forwarding of SRv6 to achieve computing power-aware routing decisions and other functions.

[0144] Specifically, the computing power requesting node is mainly responsible for generating computing power task requests or computing power request messages in the computing power routing service. In this embodiment, the computing power requesting node supports requesting computing power resources from the SRv6 computing power control center node to obtain specific computing power service identification information; it also supports carrying the computing power service identification in the computing power service traffic, and sending the computing power service traffic to the SRv6 computing power routing node to request the SRv6 computing power routing node to schedule computing power resources and provide them to the computing power requesting node.

[0145] In order to enable the SRv6 computing power routing node to parse the computing power service identification information carried in the computing power business traffic, select the corresponding computing power node according to the mapping relationship between the computing power service identification generated by the computing network resource status and multiple computing power service instance nodes, and guide the computing power service data packet to the computing power routing and forwarding actions in the corresponding SRv6 path that meets the computing power requirements, this embodiment defines a computing power service identification (Service Identifier, SID), expressed as END.C.

[0146] Step S20: Perform computing power routing scheduling based on the computing power service identifier.

[0147] It can be understood that computing power routing and scheduling means that computing power nodes with computing power resources provide computing power services to computing power request nodes. In this embodiment, the methods of computing power routing and scheduling at least include centralized routing and scheduling and distributed routing and scheduling. Centralized Overlay computing power routing means that the computing power management and control center node senses the information of computing power services and network services, and centrally arranges computing power nodes and network paths; the information of computing power services in distributed Overlay computing power routing is sensed and announced among computing power routing nodes, and the computing power routing nodes make decisions for computing power services, and other non-computing power routing node devices do not sense the computing power status information.

[0148] Computing power routing refers to dynamically sensing and coordinately scheduling computing resources and network resources in a communication network. Computing power resources are not resource data that can be transported. In fact, computing power routing means allocating computing power calculation tasks to the nodes with the optimal computing power resources, and the optimal nodes execute the allocated computing power calculation tasks, so as to realize the process of "computing power transmission" through intelligent routing decisions.

[0149] In one embodiment, in order to improve the efficiency of computing power routing, this embodiment needs to formulate a corresponding computing power routing path for computing power routing, that is, after establishing the computing power routing path between the computing power request node - computing power routing node - computing power node, then perform computing power routing and scheduling based on the computing power routing path. The computing power routing and scheduling based on the computing power service identifier includes:

[0150] Step S201: Generate a computing power routing path based on the computing power service identifier;

[0151] It should be noted that the computing power routing path is generated by the computing power routing node or the computing power management and control center node, and the generation method is determined according to the type of the computing power routing architecture. In this embodiment, the computing power routing architecture at least includes: centralized computing power routing architecture, distributed computing power routing architecture, and hybrid computing power routing architecture. Under different computing power routing architectures, the corresponding computing power routing and scheduling methods are different.

[0152] Step S202: Perform computing power routing and scheduling according to the computing power routing path.

[0153] Specifically, under the deployment of the SRv6 computing power routing centralized architecture, the SRv6 computing power management and control center node senses the status information of computing power service instances and network resources, supports the SRv6 computing power and network management and control center to collect the Service Identifier (SID) of computing power services through the Border Gateway Protocol - Link State (BGP-LS), centrally arranges the SRv6 computing power routing according to business requirements, generates the SRv6 computing power routing policy, and then issues it to the SRv6 computing power routing node for computing power service addressing and scheduling.

[0154] Under the deployment of the SRv6 computing power routing distributed architecture, the SRv6 computing power routing node senses the computing power service information and network resource status, and conducts computing power routing announcements through the distributed routing protocol. It supports the SRv6 computing power routing node to announce the computing power service identifier SID through the Interior Gateway Protocol (IGP) and the Border Gateway Protocol (BGP). The SRv6 computing power routing entry node arranges the SRv6 computing power path and schedules the computing power service to the optimal computing power node.

[0155] Under the deployment of the SRv6 computing power routing hybrid architecture, the control plane system supports the collection of centralized and distributed computing power. Considering the flexibility of computing power routing, it can be either centrally calculated or distributedly processed to meet the needs of different types of computing power services. The system can dynamically select the most suitable computing power routing calculation strategy. Whether it adopts a centralized or distributed deployment, its core goal is always to ensure the efficient scheduling of the computing power service to the node with the best performance.

[0156] Optionally, in order to adapt to the computing power routing paths under different routing architectures, step S201 includes:

[0157] Parse the computing power service identifier to obtain the computing power routing path;

[0158] and / or

[0159] Receive the computing power routing path sent by the computing power management and control center node, where the computing power routing path is arranged by the computing power management and control center node based on the computing power service identifier.

[0160] It should be understood that the computing power service identifier is generally generated by the computing power management and control center node in the SRv6 routing architecture, defined on the computing power routing node, associated with the computing power routing and forwarding table entries of the SRv6 computing power routing node, and the target field in the computing power service identifier SID records the common address for guiding multiple computing power routing nodes. After receiving the computing power service identifier SID, any computing power routing node can determine whether to participate in the computing power scheduling of this task by querying the computing power forwarding table.

[0161] In a specific implementation, in a centralized computing power routing architecture, after receiving a computing power service identifier, a computing power routing node can obtain a forwarding path for forwarding a computing power service data packet, that is, a computing power routing path, by parsing the computing power service identifier; in a distributed computing power routing architecture, a computing power management and control center node generates a computing power routing path by orchestrating the computing power service identifier. During the computing power scheduling process, the computing power management and control center node can directly send the computing power routing path to the computing power routing node to guide the forwarding process of the computing power service data packet; in a hybrid computing power routing architecture, the control plane system supports the collection of centralized and distributed computing power, and can perform both centralized computing and distributed processing to meet the requirements of different types of computing power services for the computing power routing path. Correspondingly, both parsing the computing power service identifier to obtain the computing power routing path and receiving the computing power routing path sent by the computing power management and control center node are acceptable, and this embodiment does not make specific limitations on this.

[0162] Optionally, the parsing the computing power service identifier to obtain a computing power routing path includes:

[0163] Parsing the computing power service identifier to obtain a target field for representing the public address of the computing power routing node;

[0164] When the target field meets the first forwarding condition, query the computing power routing path corresponding to the computing power service identifier through the computing power forwarding table.

[0165] In a specific implementation, the computing power forwarding table records the mapping relationship between each computing power routing node in the SRv6 computing power routing architecture, so that during the computing power scheduling process, the best scheduling path can be selected according to the mapping relationship between each computing power routing node.

[0166] The first forwarding condition means that the computing power routing node where the computing power service identifier is currently located is the same as the computing power routing node corresponding to the public address recorded in the target field. That is, when a certain computing power routing node receives the computing power service identifier and parses the target field of the public address, if the computing power routing node corresponding to the public address recorded in the target field is the same as the local computing power routing node, it is determined that the local computing power routing node participates in this computing power scheduling task.

[0167] Optionally, in order to improve the efficiency of the computing power service identifier to determine the computing power routing path, the querying the computing power routing path corresponding to the computing power service identifier through the computing power forwarding table includes:

[0168] Query the next-hop computing power routing node and the forwarding output interface corresponding to the computing power service identifier through the computing power forwarding table. The next-hop computing power routing node is the next computing power routing node that receives the computing power service identifier in the computing power routing path, and the forwarding output interface is used to send the computing power service identifier from the current computing power routing node to the next-hop computing power routing node.

[0169] As recorded above, since the computing power service identifier records the field information corresponding to the public addresses of multiple computing power routing nodes, if a certain computing power routing node determines the parameters for this computing power scheduling task, it can determine the next computing power routing node that receives the computing power service identifier through the next-hop computing power routing node recorded in the target field, and then send the computing power service identifier from the currently located computing power routing node to the next-hop computing power routing node through the outgoing interface to achieve computing power scheduling.

[0170] In one embodiment, step S202 includes:

[0171] Guiding the flow direction of the computing power service data packet carried in the computing power service request traffic based on the computing power routing path.

[0172] In a specific implementation, since computing power scheduling is essentially for a computing power node that requests to provide computing power resources to calculate or run the corresponding computing power instance, the existence form of the computing power service request is a data packet. During the computing power scheduling process, the data packet is transmitted between the computing power request node, the computing power routing node, and the computing power node to achieve the scheduling of computing power resources. Therefore, when each computing power routing node determines the computing power routing path, it can guide the flow direction of the computing power service data packet carried in the computing power service request traffic among the computing power routing nodes, shorten the transfer times of the traffic packet, and improve the efficiency of computing power scheduling.

[0173] Correspondingly, guiding the flow direction of the computing power service data packet carried in the computing power service request traffic based on the computing power routing path includes:

[0174] Sending the computing power service data packet to the next-hop computing power routing node through the outgoing interface.

[0175] The process of guiding the flow direction of the computing power service data packet is to send the computing power service data packet to the next-hop computing power routing node through the determined outgoing interface, so that the next-hop computing power routing node can parse the received computing power service data packet, obtain the computing power service identifier, and determine the computing power routing path until the computing power service request traffic is sent to the computing power routing exit node.

[0176] Optionally, sending the computing power service data packet to the next-hop computing power routing node through the outgoing interface includes:

[0177] Updating the computing power service data packet;

[0178] Sending the updated computing power service data packet to the next-hop computing power routing node through the outgoing interface.

[0179] It should be understood that since each computing power routing node will perform steps such as decompressing, parsing, and verifying the computing power service data packet after receiving it to determine whether to participate in this computing power scheduling task, in order to ensure the transmission security of the computing power data packet, in this embodiment, each computing power routing node needs to synchronously update the computing power service data packet when the computing power service data packet is sent to the next-hop computing power routing node through the forwarding egress interface.

[0180] Optionally, since there are multiple types of computing power routing nodes, the computing power routing nodes at least include a computing power routing entry node, a computing power routing intermediate node, and a computing power routing exit node, and there are certain differences in the functions supported by different computing power routing nodes.

[0181] For example: The computing power routing entry node supports the announcement of computing power resource information, supports the decision-making of SRv6 network paths, supports receiving computing power service request traffic, parses the computing power service identification information carried in the computing power service traffic, supports receiving the SRv6 path policy and service level agreement (SLA) parameters of the computing power network management and control center issued by the SRv6 computing power network management and control center, supports selecting the corresponding computing power node according to the mapping relationship between the computing power service identification generated according to the computing power network resource information and multiple computing power service instance nodes, supports guiding the computing power service data packet to the corresponding SRv6 path that meets the computing power requirements, and other functions.

[0182] The SRv6 computing power routing exit node supports the termination of the SRv6 computing power path at the SRv6 computing power routing exit node, supports the removal of the computing power service identification and external SRv6 encapsulation information at the SRv6 computing power routing exit node. It supports not removing the computing power service identification and external SRv6 encapsulation information and continuing to transmit with the computing power service traffic data packet, supports not removing the computing power service identification, and after removing the external SRv6 encapsulation information, re-encapsulating new path forwarding information into the data packet, supports receiving the computing power service SLA parameters issued by the SRv6 computing power network management and control center, supports the perception and announcement of computing power resource information, supports the decision-making of computing power nodes, and other functions.

[0183] As a result, when the computing power routing node updates the computing power service data packet, there are also multiple update methods. Correspondingly, updating the computing power service data packet includes at least one of the following methods:

[0184] Removing the computing power service identification and external SRv6 encapsulation information in the computing power service data packet;

[0185] Retaining the computing power service identification and the external SRv6 encapsulation information in the computing power service data packet;

[0186] Retaining the computing power service identification in the computing power service data packet and removing the external SRv6 encapsulation information.

[0187] Among them, the external SRv6 encapsulation information is used to encapsulate the routing extension header in the computing power service request traffic. The routing extension header is a message in the computing power service request traffic used to represent at least one computing power service identifier. The at least one computing power service identifier is respectively used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources for the computing power request node.

[0188] In one embodiment, in order to improve the efficiency of computing power scheduling, it is necessary to determine in advance the computing power resources that each computing power node can provide to prevent the failure of computing power calculation tasks. The routing method further includes:

[0189] Perceiving computing power resource information.

[0190] It should be noted that the computing power resource information includes at least one of the following: computing power information used to represent the attributes, status, and / or performance of the computing power resource device; network information used to represent the topology, link attributes, and / or SRv6 routing policy of each computing power routing node in the computing power scheduling device, etc.

[0191] Optionally, the perceiving of the computing power resource information includes:

[0192] When the SRv6 computing power routing architecture is a distributed computing power routing architecture or a hybrid computing power routing architecture, perceiving the computing power resource information.

[0193] When generating the computing power routing path, the computing power routing path of the centralized routing architecture is issued by the computing power management and control center node. Under the distributed routing architecture or the hybrid routing architecture, the computing power routing path is extended by the computing power routing node itself based on the IGP or BGP protocol, and the computing power information is transmitted between devices. The computing power information also includes the SRv6 SID information defined on the computing power routing node, and the device selects the route comprehensively according to the computing power information.

[0194] In specific implementation, for the sake of easy understanding, under the distributed routing architecture, refer to Figure 5 , Figure 5 , which is a schematic diagram of the distributed multi-computing power instance computing power routing scenario in this embodiment. Among them, computing power nodes A and B provide the same computing power service. Initially, the computing power service is provided by computing power node A; when the load of computing power node A reaches or exceeds a certain threshold n%, the newly accessed computing power service is provided by computing power node B; when the load of computing power node A drops to a certain threshold, the newly accessed service is still provided by computing power node A; when there is a new service access, its subsequent packets are fixed for processing on the original path to maintain the stickiness of the service flow.

[0195] Further, refer to Figure 6 , Figure 6This is a schematic diagram of the service chain scenario supported under the SRv6 network architecture in this embodiment. Among them, computing power node A provides computing power service SFA, and computing power node B provides computing power services SFA and SFB; the service process is processed through SFA - SFB, and the packet path of the newly accessed service is PC3 - PE3 - PE1 - SFA - PE1 - PE2 - SFB - PE2 - PC2; when the service increases and the processing capacity of SFA in computing power node A reaches the threshold, the newly accessed service is provided with SFA service by computing power node B, and the packet path is PC3 - PE3 - PE2 - SFA - PE2 - SFB - PE2 - PC2; when the service drops or the service volume decreases and SFA service can continue to be provided in computing power node A, the newly accessed service is provided with SFA service by computing power node A, and the packet path is PC3 - PE3 - PE1 - SFA - PE1 - PE2 - SFB - PE2 - PC2; when a new service is accessed, the computing power request packet corresponding to the new service is fixed on the original path for processing to maintain the stickiness of the service flow.

[0196] In one embodiment, to better schedule computing power resources, the method further includes:

[0197] Sending computing power notification information.

[0198] It should be understood that in the face of multiple computing power calculation tasks, the computing power resources of some computing power nodes may be insufficient to support the completion of these computing power calculation tasks. At this time, each node supporting the SRv6 function can broadcast its current computing resource status, such as CPU usage rate, memory occupancy, storage space, and available service instances, etc., to other parts of the network through a specific protocol or mechanism, so as to dynamically perceive the computing power resources on different nodes and make more intelligent computing power scheduling decisions based on this.

[0199] In this embodiment, the computing power notification information at least includes: an extended SRv6 computing power service TLV packet, and the extended SRv6 computing power service TLV packet carries an SRv6 computing power service identifier; the extended SRv6 computing power service TLV packet is defined according to the target routing advertisement protocol corresponding to the SRv6 computing power routing architecture; the SRv6 computing power routing architecture is a centralized computing power routing architecture, a distributed computing power routing architecture, or a hybrid computing power routing architecture.

[0200] The computing power service SID is advertised between computing power routing nodes or between a computing power routing node and an SRv6 computing network control center through an extended distributed routing protocol, and the extended distributed routing protocol, that is, the target routing advertisement protocol, at least includes an interior gateway protocol, a border gateway protocol, and / or a border gateway - link state protocol.

[0201] Optionally, the extended SRv6 computing power service TLV message under the Border Gateway Protocol includes at least one of the following:

[0202] TLV type field;

[0203] TLV length field;

[0204] Reserved field;

[0205] At least one first TLV field of the SRv6 computing power service.

[0206] Specifically, referring to Table 1, Table 1 is the new SRv6 Service Sub-TLV proposed in this embodiment, which is the SRv6 computing power service TLV, that is, SRv6 Compute Service TLV. Its encoding form in the BGP Prefix-SID attribute is:

[0207] Table 1

[0208]

[0209] Optionally, when the TLV type field is a preset type, at least one first TLV field of the SRv6 computing power service carries a SRv6 computing power service calculation TLV field, and a computing power service identifier is carried in the SRv6 computing power service calculation TLV field.

[0210] In specific implementation, the TLV Type is used to represent the type of the subtype length value field of service-specific information, the TLV length field is used to represent the length of the subtype length value field of service-specific information, and the SRv6 Service Sub-TLVs (Type-Length-Value subtype) is a structure used to carry SID (Segment Identifier) information related to a specific service in the control plane protocol, and is usually embedded in a higher-level TLV to provide detailed information on how to process a specific prefix or service.

[0211] In this embodiment, taking the preset type TLV Type = 10 as an example, it indicates that the SRv6 Service Sub-TLVs (variable) field carries the SRv6 Compute Service TLV, in which the SRv6 SID of the computing power service is carried. If the TLV Type = 10 in IANA and IETF is used for the definition of other TLV types, the corresponding data should be adjusted accordingly or adjusted after negotiation with IANA or IETF.

[0212] Optionally, the SRv6 computing power service calculation TLV field includes at least one of the following:

[0213] The first type field of the first TLV;

[0214] The length field of the first TLV;

[0215] The first reserved field;

[0216] The numerical value field of the SRv6 computing power service identifier;

[0217] The control identifier field of the computing power service identifier;

[0218] The interface behavior field of the SRv6 computing power service identifier;

[0219] The second reserved field;

[0220] At least one second TLV field of the SRv6 computing power service data.

[0221] In a specific implementation, the SRv6 computing power service calculates the TLV field, that is, the encoding form of the SRv6 Compute Service TLV is shown in Table 2:

[0222] Table 2

[0223]

[0224] Among them, Sub-TLV Type is the type identifier of the first TLV, used to identify the type of the first TLV, Sub-TLVLength is the length field of the first TLV used to identify the length of the first TLV field, Reserved1 is the first reserved field, SRv6 SID Value is the numerical value field of the SRv6 computing power service identifier, used to identify different computing power service identifiers, Svc SIDFlags is the control identifier field of the computing power service identifier, used to indicate specific forwarding behaviors or features, SRv6 SIDEndpoint Behavior is the interface behavior field of the SRv6 computing power service identifier, used to indicate a series of operations that the node should perform when a data packet arrives at a node with a specific SID, these behaviors are determined by the functional part defined in the SID, and can implement various complex network services and functions, Reserved2 is the second reserved field, and SRv6 ServiceData Sub-Sub-TLVs is at least one second TLV field of the SRv6 computing power service data.

[0225] Optionally, at least one second TLV field of the SRv6 computing power service data includes at least one of the following at least:

[0226] The first type field of the second TLV;

[0227] Second TLV length field;

[0228] First position identifier length field;

[0229] Second position identifier length field;

[0230] Function identifier length field;

[0231] Variable identifier length field;

[0232] Conversion character length field;

[0233] Conversion offset field.

[0234] At least one second TLV field of SRv6 computing power service data, that is, the encoding form of the SRv6 Service Data Sub-Sub-TLV field is shown in Table 3:

[0235] Table 3

[0236]

[0237] Among them, Sub-Sub-TLV Type is the first type field of the second TLV, Sub-Sub-TLV Length is the second TLV length field, Locator Block Length is the first location identifier length field, which is used to characterize how to allocate and use SID (Segment Identifier) in the IPv6 address space. Locator is a prefix used to identify one or more nodes in the network, while Block is a part of Locator, usually representing the common prefix part of a subnet. Locator Node Length is the second location identifier length field, which is used to identify the length of the node (Node ID). Function Length is the function identifier length field, which is used to characterize the identification of specific forwarding instructions or behaviors. Argument Length is the variable identifier length field, which is used to execute specific operations or service functions. TranspositionLength is the transposition character length field, which is the number of bits involved in the SID (Segment ID) transposition operation and is used to indicate how to handle the SID in the IPv6 address, especially when these SIDs are used to represent specific segments or services on the network path. Transposition Offset is the transposition offset field, which is used to characterize the offset of a certain SID in the SID list relative to the starting position, and the Locator Block Length, Locator Node Length, Function Length, and Argument Length fields correspond to the lengths of the Locator Block, Locator Node, Function, and Argument of the computing power service identifier.

[0238] In one embodiment, the extended SRv6 computing power service TLV packet under the internal gateway protocol at least includes:

[0239] At least one of the type field, length field, control identifier field, SRv6 interface function field, computing power service identifier field, the length field of the second TLV, and at least one second TLV field;

[0240] Or

[0241] At least one of the type field, length field, control identifier field, reserved field, interaction interface identifier field, computing power service identifier field, and at least one second TLV field.

[0242] In a specific implementation, this embodiment defines an extended SRv6 computing power service TLV message under the interior gateway protocol, namely the SRv6 END.C SID Sub-TLV. The Endpoint Behaviour number is, for example, 200. If the Endpoint Behaviour number in IANA and IETF = 200 is used for the definition of other TLV types, the extended SRv6 computing power service TLV message under the interior gateway protocol can be adjusted accordingly or adjusted after negotiation with IANA or IETF. The encoding forms of the SRv6 END.C SID Sub-TLV in ISISv6 and OSPFv are shown in Table 4 and Table 5 respectively:

[0243] Table 4

[0244]

[0245] Among them, Type is the type field, Length is the length field, Flags is the control flag field, SRv6EndpointFunction is the SRv6 interface function field, SID is the computing power service identification field, Sub-sub-TLV-Len is the length field of the second TLV, and Sub-sub-TLVs(Variable) is the second TLV field.

[0246] Table 5

[0247]

[0248] Among them, Type is the type field, Length is the length field, Flags is the control flag field, Reserved is the reserved field, Endpoint Behaviour ID is the interaction interface identification field, which is used to indicate the function identification of a series of operations that should be performed by a node when a data packet arrives at a node with a specific SID. SID is the computing power service identification field, and Sub-sub-TLVs(Variable) is the second TLV field.

[0249] In one embodiment, the extended SRv6 computing power service TLV under the border gateway - connection state protocol further includes: an SRv6 computing power service information TLV message and an SRv6 interface function TLV message;

[0250] Among them, the SRv6 computing power service information TLV message includes at least one of the type field, the length field, and the computing power service identification field;

[0251] The SRv6 interface function TLV message includes at least one of the type field, the length field, the SRv6 interface function identification field, the control flag field, and the algorithm identification field.

[0252] The computing power service SID is filled in the SRv6 SID Information TLV, and the corresponding EndpointBehaviour number is also filled in the SRv6 Endpoint Function TLV. The encoding forms of the SRv6 computing power service information TLV message and the SRv6 interface function TLV message are shown in Tables 6 and 7 as follows:

[0253] Table 6

[0254]

[0255] Table 7

[0256]

[0257] In this embodiment, the computing power routing node receives the computing power service request traffic from the computing power request node, and performs computing power routing scheduling based on the computing power service identifier, so as to improve the utilization rate of computing power resources in the SRv6 network.

[0258] Reference Figure 7 , Figure 7 is the schematic flow chart of the second embodiment of the routing method of the present invention.

[0259] In this embodiment, the routing method is applied to the computing power management and control center node, and the computing power management and control center node is connected to the computing power routing node. The method includes:

[0260] Step S30: Send the segment identifier list of the computing power service to the computing power request node.

[0261] It should be noted that the execution subject of this embodiment can be a programmable device supporting SRv6, such as a computing power management and control device that realizes functions such as computing power perception or routing decision-making, for example: a routing server or a routing cabinet, etc., or other computing power management and control devices that can realize the above functions. This embodiment does not make specific limitations on this.

[0262] The segment identifier list includes at least one computing power service identifier, and each computing power service identifier is respectively used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources for the computing power request node.

[0263] Specifically, in the SRv6 computing power service function programming, the combination of the computing power service SID that supports identifying the computing power service and the SID that identifies the SRv6 forwarding path is supported, and the combination of multiple SIDs that identify the computing power service is supported, so that the computing power service traffic can realize the service function chain (Service Function Chaining, SFC) at the L3 network layer between SRv6 computing power routing nodes.

[0264] In addition, this embodiment also supports identifying computing power service functions through the combination of Locator + Function + Argument. The Locator is the common address prefix of the SRv6 computing power routing node or its gateway, the Function is the computing power service function identifier, and the Arguments are the optional parameters of the Function.

[0265] By encapsulating a series of segment identifier lists and computing power service identifiers in the Segment Routing Header (SRH), it can be used to guide the computing power request traffic or computing power request messages to be forwarded between SRv6 computing power routing nodes according to the planned and choreographed path. The SRv6 computing power routing node strips the SRH and locally caches the remaining SRH, forwards the message to the computing power service instance, and when the computing power service instance sends out a message to the next computing power service, re-encapsulates the remaining SRH and forwards it to the next-hop SRv6 computing power routing node.

[0266] Optionally, the routing method further includes:

[0267] Perceiving computing power resource information;

[0268] It should be noted that the computing power resource information at least includes at least one of the following: computing power information used to characterize the attributes, status, and / or performance of the computing power resource device; network information used to characterize the topology, link attributes, and / or SRv6 routing policy of each computing power routing node in the computing power scheduling device, etc.

[0269] Optionally, the perceiving of the computing power resource information includes:

[0270] When the SRv6 computing power routing architecture is a centralized computing power routing architecture or a hybrid computing power routing architecture, perceiving the computing power resource information.

[0271] Different from the perception of computing power resource information through computing power routing nodes in the above text, in the case of adopting a centralized routing architecture, the SRv6 computing power and network control center perceives the status information of computing power service instances and the status of network resources, supports the SRv6 computing power and network control center to collect computing power service SIDs through BGP-LS, centrally choreographs SRv6 computing power routes according to service requirements, generates SRv6 computing power routing policies and then distributes them to SRv6 computing power routing nodes for computing power service addressing and scheduling. In the deployment of the SRv6 computing power routing hybrid architecture, the control plane system supports the collection of centralized and distributed computing power. Considering the flexibility of computing power routing, it can be either centrally calculated or distributedly processed to meet the needs of different types of computing power services.

[0272] Optionally, the perceiving of the computing power resource information includes:

[0273] The computing power management and control center node obtains computing power resource information based on at least one of the Interior Gateway Protocol, Border Gateway Protocol, and Border Gateway - Link State Protocol.

[0274] and / or

[0275] The computing power management and control center node obtains computing power resource information based on the new computing network integrated announcement protocol.

[0276] In a specific implementation, the SRv6 computing power management and control center node senses the status information of computing power service instances and network resources, supports the SRv6 computing network management and control center to collect the Service Identifier (SID) of computing power services through the Border Gateway Protocol - Link State (BGP - LS), centrally arranges the SRv6 computing power routes according to service requirements, generates SRv6 computing power routing policies, and then distributes them to SRv6 computing power routing nodes for computing power service addressing and scheduling.

[0277] The computing power information and network information are independently obtained through protocols such as the Border Gateway Protocol (BGP), Border Gateway - Link State Protocol (BGP - LS), Telemetry, and existing protocol interfaces of the cloud management platform, or the computing power and network information can be obtained together through the new computing network integrated announcement protocol.

[0278] Optionally, the computing power resource information includes at least one of the following:

[0279] Computing power information used to characterize the attributes, status, and / or performance of the computing power resource device;

[0280] Network information used to characterize the topology, link attributes, and / or SRv6 Policy policies of each computing power routing node in the computing power scheduling device;

[0281] The computing power information is obtained through at least one of the Interior Gateway Protocol, Border Gateway Protocol, RESTful interface, and distributed database:

[0282] The network information is obtained through the Border Gateway - Link State Protocol and / or Telemetry.

[0283] In a specific implementation, the computing power management and control node center supports realizing the perception of computing power resources through middleware facilities such as IGP, BGP protocol, RESTful interface, and distributed database, and perceiving the attributes, status, performance, etc. of computing power resources; it supports realizing the perception of network resources through BGP - LS, Telemetry, and perceiving the topology, link attributes, SRv6 Policy attributes, etc. of the network.

[0284] Optionally, generating a segment identifier list carrying at least one computing power service identifier based on the computing power resource information includes:

[0285] Create a computing power service identifier;

[0286] Associate the computing power service identifier with the computing power resource information to obtain at least one computing power service identifier for identifying at least one computing power service instance;

[0287] Generate a segment identifier list of the computing power service according to the at least one computing power service identifier.

[0288] It can be understood that in this embodiment, Segment programming is performed for the computing power service, and the SRv6 SID is used to identify the computing power service. Each SID identifies a computing power service function. In the SRv6 computing power service function programming, the combination of the computing power service SID for identifying the computing power service and the SID for identifying the SRv6 forwarding path is supported, and the combination of multiple segment identifier lists for identifying the computing power service is supported, so that the computing power service traffic can implement the L3 network layer SFC service function chain between SRv6 computing power routing nodes.

[0289] This embodiment also identifies the computing power service function through the combination of Locator + Function + Argument. The Locator is the common address prefix of the SRv6 computing power routing node or its gateway, the Function is the computing power service identifier, and the Arguments are the optional parameters of the Function.

[0290] Optionally, the method further includes:

[0291] Send a computing power routing path to the computing power routing node, for instructing the computing power routing node to perform computing power routing scheduling or guiding the flow direction of the computing power service request traffic.

[0292] The computing power service request traffic is sent from the computing power request node to the computing power routing node.

[0293] It should be noted that the computing power routing path is generated by the computing power routing node or the computing power management and control center node, and the generation method is determined according to the type of the computing power routing architecture. This embodiment does not elaborate on this too much. Since the computing power scheduling is essentially the calculation or operation of the corresponding computing power instance by the computing power node that requests to provide computing power resources, the existence form of the computing power service request is a data packet. During the computing power scheduling process, the data packet is transmitted between the computing power request node, the computing power routing node, and the computing power node to achieve the scheduling of the computing power resources. Therefore, when each computing power routing node determines the computing power routing path, it can shorten the number of times the traffic packet is transferred by guiding the flow direction of the computing power service data packet carried in the computing power service request traffic, and improve the efficiency of the computing power scheduling.

[0294] Optionally, before sending the computing power routing path to the computing power routing node, it further includes:

[0295] Orchestrate computing power service identifiers based on the user service computing power request to generate a computing power routing path. The user service computing power request is sent by the computing power request node and is used to characterize the computing power load of the computing power request node.

[0296] The user service computing power request includes the minimum computing power load for completing the user's computing service. Determine the target computing power node that can provide this minimum computing power load through the computing power management and control center node, and determine the routing path between the computing power request node and the target computing power node, so as to obtain the optimal computing power scheduling path for this user service.

[0297] In this embodiment, the computing power management and control center node sends a list of segment identifiers of the computing power service to the computing power request node, so that the computing power request node generates computing power service request traffic according to user requirements, improving the service processing efficiency of users in the SRv6 network architecture.

[0298] Reference Figure 8 , Figure 8 is a schematic flowchart of the third embodiment of the routing method of the present invention.

[0299] In this embodiment, the routing method is applied to a computing power request node, and the computing power request node is connected to the computing power routing node. The method includes:

[0300] Step S40: Send computing power service request traffic to the computing power routing node.

[0301] It should be noted that the execution subject of this embodiment can be a terminal device with data processing, network communication, and program running functions, such as a control computer, a terminal server, or other devices with computing power service requirements. This embodiment does not make specific limitations on this.

[0302] It can be understood that the computing power service request traffic carries at least one computing power service identifier, and the computing power service identifier is sent by the computing power management and control center node to the computing power request node.

[0303] Optionally, before sending the computing power service request traffic to the computing power routing node, it further includes:

[0304] Generate computing power service request traffic according to the list of segment identifiers of the computing power service, and the list of segment identifiers of the computing power service is sent by the computing power management and control center node.

[0305] In specific implementation, the list of segment identifiers includes at least one computing power service identifier, and each computing power service identifier is respectively used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources to the computing power request node.

[0306] Before generating the computing power service request traffic according to the segment identifier list of the computing power service, it further includes:

[0307] Sending a user service computing power request to the computing power management center node to request the computing power management center node to issue a computing power service identifier.

[0308] The user service computing power request includes the minimum computing power load for completing the user's computing service. The target computing power node capable of providing this minimum computing power load is determined through the computing power management center node, and the routing path between the computing power request node and the target computing power node is determined, so as to obtain the optimal computing power scheduling path for this user service.

[0309] In this embodiment, the computing power service request traffic is sent to the computing power routing node to request the computing power routing node to guide the computing power service request traffic to the computing power node that meets the service requirements of the computing power request node, thereby solving the service requirements of the computing power request node.

[0310] This application provides a routing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the routing method in the first embodiment above.

[0311] Next, refer to Figure 9 , which shows a schematic structural diagram of a routing device suitable for implementing the routing device of the embodiment of this application. The routing device in the embodiment of this application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 9 The routing device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0312] As Figure 9As shown, the routing device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the routing device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the routing device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a routing device having various systems, it should be understood that it is not required to implement or have all the systems shown. Instead, more or fewer systems may be implemented or had.

[0313] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0314] The routing device provided by the present application adopts the routing method in the above embodiment and can solve the technical problems of routing. Compared with the prior art, the beneficial effects of the routing device provided by the present application are the same as those of the routing method provided by the above embodiment, and the other technical features in the routing device are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0315] It should be understood that the various parts disclosed in the present application may be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0316] As described above, this is only the specific implementation manner of the present application. However, the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the said claims.

[0317] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the routing method in the above-mentioned embodiments.

[0318] The computer-readable storage medium provided by the present application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0319] The above-mentioned computer-readable storage medium can be included in a routing device; it can also exist separately without being assembled into the routing device.

[0320] The above-mentioned computer-readable storage medium carries one or more programs. When the one or more programs are executed by a routing device, the routing device is caused to: route.

[0321] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0322] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0323] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0324] The readable storage medium provided in this application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned routing method, which can solve the technical problems of routing. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the routing method provided in the above embodiments, and will not be elaborated here.

[0325] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the routing method as described above.

[0326] The computer program product provided by the present application can solve the technical problem of routing. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the routing method provided by the above embodiments, and will not be elaborated herein.

[0327] The above are only some embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

[0328] In the above description, reference is made to the accompanying drawings which form a part of the present application and show specific aspects of the embodiments of the present application or aspects in which the embodiments of the present application can be used. It should be understood that the embodiments of the present application can be used in other aspects and can include structural or logical changes not depicted in the accompanying drawings. For example, it should be understood that the disclosure of the described method can be equally applicable to the corresponding device or system for performing the method, and vice versa. For example, if one or more specific method steps are described, the corresponding device can include one or more units such as functional units to perform the one or more described method steps (e.g., one unit performs one or more steps, or multiple units, each of which performs one or more of the multiple steps), even if such one or more units are not explicitly depicted or described in the accompanying drawings. On the other hand, for example, if a specific device is described based on one or more units such as functional units, the corresponding method can include a step to perform the functionality of the one or more units (e.g., one step performs the functionality of the one or more units, or multiple steps, each of which performs the functionality of one or more of the multiple units), even if such one or more steps are not explicitly depicted or described in the accompanying drawings. Further, it should be understood that, unless otherwise explicitly stated, the features of the various exemplary embodiments and / or aspects described herein can be combined with each other.

Claims

1. A routing method, characterized in that: The method is applied to a computing power routing node, and the method comprises: Receive computing power service request traffic from a computing power requesting node, wherein the computing power service request traffic carries at least one computing power service identifier, and the computing power service identifier is sent by a computing power control center node to the computing power requesting node; Computing power routing scheduling is performed based on the computing power service identifier.

2. The routing method according to claim 1, characterized in that: The performing computing power routing scheduling based on the computing power service identifier includes: Generate a computing power routing path based on the computing power service identifier; Computing power routing scheduling is performed according to the computing power routing path.

3. The routing method according to claim 2, characterized in that: The generating a computing power routing path based on the computing power service identifier includes: Parse the computing power service identifier to obtain a computing power routing path; and / or Receive a computing power routing path sent by the computing power control center node, where the computing power routing path is arranged by the computing power control center node based on the computing power service identifier.

4. The routing method according to claim 3, characterized in that: The step of parsing the computing power service identifier to obtain a computing power routing path includes: Parsing the computing power service identifier to obtain a target field for representing a public address of a computing power routing node; When the target field satisfies the first forwarding condition, the computing power routing path corresponding to the computing power service identifier is queried through the computing power forwarding table.

5. The routing method according to claim 4, characterized in that: The method comprises at least one of the following: The computing power forwarding table records the mapping relationship between each computing power routing node in the SRv6 computing power routing architecture; The SRv6 computing power routing architecture is composed of a computing power request node, a computing power resource node, a computing power control center node and at least one computing power routing node; The first forwarding condition includes: the computing power routing node where the computing power service identifier is currently located is the same as the computing power routing node corresponding to the public address recorded in the target field.

6. The routing method according to claim 4, characterized in that: The querying the computing power routing path corresponding to the computing power service identifier through the computing power forwarding table includes: The next-hop computing power routing node and the forwarding interface corresponding to the computing power service identifier are queried through the computing power forwarding table. The next-hop computing power routing node is the next computing power routing node in the computing power routing path that receives the computing power service identifier. The forwarding interface is used to send the computing power service identifier from the current computing power routing node to the next-hop computing power routing node.

7. The routing method according to claim 2, characterized in that: The performing computing power routing scheduling according to the computing power routing path includes: The flow direction of the computing power service data packet carried in the computing power business request traffic is guided based on the computing power routing path.

8. The routing method according to claim 7, characterized in that: The guiding the flow direction of the computing power service data packet carried in the computing power business request flow based on the computing power routing path includes: The computing power service data packet is sent to the next-hop computing power routing node through the forwarding interface.

9. The routing method according to claim 8, characterized in that: The step of sending the computing power service data packet to the next-hop computing power routing node through a forwarding interface includes: Updating the computing power service data package; The updated computing power service data packet is sent to the next-hop computing power routing node through the forwarding interface.

10. The routing method according to claim 9, characterized in that: The updating of the computing power service data packet includes at least one of the following methods: Remove the computing power service identifier and external SRv6 encapsulation information in the computing power service data packet; Retain the computing power service identifier and the external SRv6 encapsulation information in the computing power service data packet; The computing power service identifier in the computing power service data packet is retained, and the external SRv6 encapsulation information is removed.

11. The routing method according to claim 10, characterized in that: The external SRv6 encapsulation information is used to encapsulate the routing extension header in the computing power service request traffic, and the routing extension header is a message in the computing power service request traffic used to characterize at least one computing power service identifier, and the at least one computing power service identifier is used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources to the computing power requesting node.

12. The routing method according to claim 1, characterized in that: The method further comprises: Perceive computing resource information; The computing resource information includes at least one of the following: Computing power information used to characterize the properties, status and / or performance of the computing power resource device; Network information used to characterize the topology, link attributes and / or SRv6 routing strategy of each computing power routing node in the computing power scheduling device.

13. The routing method according to claim 12, characterized in that: The perceived computing power resource information includes: When the SRv6 computing power routing architecture is a distributed computing power routing architecture or a hybrid computing power routing architecture, computing power resource information is perceived.

14. The routing method according to claim 1, characterized in that: The method further comprises: Send computing power notification information.

15. The routing method according to claim 14, characterized in that: The computing power notification information at least includes: Extends SRv6 computing service TLV packets.

16. The routing method according to claim 15, characterized in that: The method comprises at least one of the following: The extended SRv6 computing power service TLV message carries an SRv6 computing power service identifier; The extended SRv6 computing power service TLV message is obtained according to the target routing announcement protocol definition corresponding to the SRv6 computing power routing architecture; The SRv6 computing power routing architecture is a centralized computing power routing architecture, a distributed computing power routing architecture, or a hybrid computing power routing architecture; The target routing advertisement protocol at least includes an interior gateway protocol, a border gateway protocol and / or a border gateway-link state protocol.

17. The routing method according to claim 16, characterized in that: The extended SRv6 computing service TLV message under the border gateway protocol includes at least one of the following: TLV type field; TLV length field; Reserved fields; At least one first TLV field of the SRv6 computing service.

18. The routing method according to claim 17, characterized in that: When the TLV type field is a preset type, at least one first TLV field of the SRv6 computing service carries an SRv6 computing service calculation TLV field, and the SRv6 computing service calculation TLV field carries a computing service identifier.

19. The routing method according to claim 18, characterized in that: The SRv6 computing service calculation TLV field includes at least one of the following: A first type field of a first TLV; The length field of the first TLV; The first reserved field; The numeric field of the SRv6 computing power service identifier; The control identification field of the computing power service identification; The interface behavior field of the SRv6 computing service identifier; The second reserved field; At least one second TLV field of SRv6 computing service data.

20. The routing method according to claim 19, characterized in that: The at least one second TLV field of the SRv6 computing power service data includes at least one of the following: The first type field of the second TLV; Second TLV length field; The first position identifies the length field; The second position identifies the length field; Function identification length field; Variable identification length field; Convert character length field; Convert the offset field.

21. The routing method according to claim 16, characterized in that: The extended SRv6 computing service TLV message under the internal gateway protocol includes at least: At least one of a type field, a length field, a control identification field, an SRv6 interface function field, a computing service identification field, a length field of a second TLV, and at least one second TLV field; or At least one of a type field, a length field, a control identification field, a reserved field, an interactive interface identification field, a computing power service identification field, and at least one second TLV field.

22. The routing method according to claim 16, characterized in that: The extended SRv6 computing power service TLV under the border gateway-connection state protocol also includes: SRv6 computing power service information TLV message and SRv6 interface function TLV message; The SRv6 computing power service information TLV message includes at least one of a type field, a length field, and a computing power service identification field; The SRv6 interface function TLV message includes at least one of a type field, a length field, an SRv6 interface function identification field, a control identification field, and an algorithm identification field.

23. A routing method, characterized in that: The method is applied to a computing power control center node, and the method includes: A segment identifier list of a computing power service is sent to a computing power requesting node, wherein the segment identifier list includes at least one computing power service identifier.

24. The routing method according to claim 23, characterized in that: The at least one computing power service identifier is used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources to the computing power requesting node.

25. The routing method according to claim 23, characterized in that: The routing method further includes: Perceive computing resource information; A segment identifier list carrying at least one computing power service identifier is generated based on the computing power resource information.

26. The routing method according to claim 25, characterized in that: The perceived computing power resource information includes: When the SRv6 computing power routing architecture is a centralized computing power routing architecture or a hybrid computing power routing architecture, computing power resource information is perceived, and the SRv6 computing power routing system is composed of a computing power request node, a computing power resource node, a computing power management and control center node and / or at least one computing power routing node.

27. The routing method according to any one of claims 25 or 26, characterized in that: The perceived computing power resource information includes: Obtain computing power resource information through the computing power control center node based on at least one of the internal gateway protocol, the border gateway protocol, and the border gateway-connection state protocol; and / or Obtain computing power resource information through the computing power control center node based on the new computing network integrated notification protocol.

28. The routing method according to claim 27, characterized in that: The computing resource information includes at least one of the following: Computing power information used to characterize the properties, status and / or performance of the computing power resource device; Network information used to characterize the topology, link attributes and / or SRv6 Policy strategy of each computing power routing node in the computing power scheduling device; The computing power information is obtained through at least one of an internal gateway protocol, a border gateway protocol, a RESTful interface, and a distributed database: The network information is obtained through the Border Gateway-Link State Protocol and / or Telemetry.

29. The routing method according to claim 23, characterized in that: The generating, based on the computing power resource information, a segment identifier list carrying at least one computing power service identifier comprises: Create a computing power service identifier; Associating the computing power service identifier with the computing power resource information to obtain at least one computing power service identifier for identifying at least one computing power service instance; A segment identifier list of the computing power service is generated according to the at least one computing power service identifier.

30. The routing method according to claim 23, characterized in that: The method further comprises: Send a computing power routing path to the computing power routing node to instruct the computing power routing node to perform computing power routing scheduling or guide the flow of computing power service request traffic.

31. The routing method according to claim 30, characterized in that: The computing power service request traffic is sent from the computing power requesting node to the computing power routing node.

32. The routing method according to claim 30, characterized in that: Before sending the computing power routing path to the computing power routing node, the method further includes: A computing power service identifier is arranged based on a user business computing power request to generate a computing power routing path. The user business computing power request is sent by a computing power requesting node and is used to characterize the computing power load of the computing power requesting node.

33. A routing method, characterized in that: The method is applied to a computing power requesting node, and the method comprises: Send computing power service request traffic to the computing power routing node, wherein the computing power service request traffic carries at least one computing power service identifier.

34. The routing method according to claim 33, characterized in that: Before sending the computing power service request traffic to the computing power routing node, the method further includes: The computing power service request flow is generated according to the segment identification list of the computing power service, and the segment identification list of the computing power service is sent by the computing power control center node.

35. The routing method according to claim 34, characterized in that: The segment identifier list includes at least one computing power service identifier, and the at least one computing power service identifier is used to identify at least one computing power service instance, and the computing power service instance is used to provide computing power services or computing power resources to the computing power requesting node.

36. The routing method according to claim 34, characterized in that: Before generating the computing power service request flow according to the segment identification list of the computing power service, the method further includes: Send a user business computing power request to the computing power control center node to request the computing power control center node to issue a computing power service identifier.

37. A routing architecture, characterized in that: The routing architecture includes: a computing power request node, a computing power control center node, and at least one computing power routing node; Wherein, the at least one computing power routing node is used to execute the routing method as described in any one of claims 1 to 22 above; The computing power control center node is used to execute the routing method as described in any one of claims 23 to 32 above; The computing power requesting node is used to execute the routing method as described in any one of claims 33 to 36 above.

38. The routing architecture of claim 37, wherein: The routing architecture also includes: a computing power resource node, which is used to provide computing power services or computing power resources.

39. A routing device, characterized in that: The routing device comprises: a memory, a processor, and a routing program stored in the memory and executable on the processor, wherein the routing program is configured to implement the routing method according to any one of claims 1 to 22, 23 to 32, or 33 to 36.

40. A storage medium, characterized in that The storage medium stores a routing program, and when the routing program is executed by the processor, the routing method according to any one of claims 1 to 22, 23 to 32, or 33 to 36 is implemented.

41. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the routing method according to any one of claims 1 to 22 or 23 to 32 or 33 to 36.

Images