Data transmission control method and device

The SDGP-ID based data transmission control method optimizes interface resource utilization by separating forwarding resources for different service flows, addressing the inefficiencies in network device interface selection and reducing resource wastage.

JP7596368B2Active Publication Date: 2024-12-09HUAWEI TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2022515902
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2019-11-22
Filing Date
2020-07-30
Publication Date
2024-12-09
Estimated Expiration
2040-07-30

AI Technical Summary

Technical Problem

Network devices waste interface resources by randomly selecting interfaces for data packet forwarding, leading to inefficiencies as some interfaces remain idle while others are overutilized, especially in network slicing scenarios.

Method used

Implement a data transmission control method that uses self-definition global policy identification (SDGP-ID) to determine interface resource objects for forwarding data packets, ensuring that different service flows utilize distinct transmission paths and reducing resource wastage by reusing topology route calculation results.

Benefits of technology

This approach optimizes interface resource utilization by separating forwarding resources for different service flows, reducing waste and improving efficiency in network slicing scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007596368000009
    Figure 0007596368000009
  • Figure 0007596368000010
    Figure 0007596368000010
  • Figure 0007596368000011
    Figure 0007596368000011
Patent Text Reader

Abstract

This application discloses a data transmission control method and apparatus for solving the problem of resource waste. In this application, one or more identification information is added to determine an interface resource object for forwarding a data packet at an interface of a network device. The one or more added identification information includes one global identification information. The global identification information can correspond to a network slice, and different network slices correspond to different values ​​of the global identification information. The global network identifier corresponds to one or more interface resource objects. One interface resource object may be occupied by only one network slice, or one interface resource object may be jointly shared by multiple network slices.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] This application claims priority to Chinese Patent Application No. 201910860821.5, entitled "Data Transmission Control Method and Apparatus", filed with the State Intellectual Property Office of the People's Republic of China on September 11, 2019, and also claims priority to Chinese Patent Application No. 201911159775.2, entitled "Data Transmission Control Method and Apparatus", filed with the State Intellectual Property Office of the People's Republic of China on November 22, 2019, which are incorporated by reference in their entireties.

[0002] TECHNICAL FIELD The embodiments of this application relate to the field of communication technology, and in particular to a data transmission control method and device. [Background technology]

[0003] Currently, during service flow forwarding, a network device usually finds a next-hop network device based on a destination address in a data packet, and then forwards the data packet to the next-hop network device. However, a network device may have multiple interfaces to communicate with a next-hop network device. In this case, the network device usually randomly selects an interface to forward a data packet to a next-hop network device, or selects an interface based on the activity state of the interface. As a result, forwarding resources cannot be separated for different service flows, and some interfaces may remain unselected, resulting in a waste of interface resources. Summary of the Invention

[0004] The embodiments of this application provide a data transmission control method and device to solve the problem of interface resource waste. [Means for solving the problem]

[0005] According to a first aspect, an embodiment of this application provides a data transmission control method. In the method, a first network device obtains a first data packet carrying a destination address and first identification information. Then, the first network device determines a target interface based on the destination address. The target interface is an interface present on the first network device and configured to connect to a second network device. The second network device is a next-hop network device of the first network device. Further, the first network device determines at least one interface resource object on the target interface based on the first identification information, and forwards the first data packet to the second network device by using the at least one interface resource object.

[0006] In this embodiment, the first identification information may be referred to as a self-definition global policy identification (SDGP ID for short). The SDGP ID has a global meaning and is used to select a forwarding resource (interface resource object). It is understood that the global identification information may alternatively be named another name. Different values ​​of the first identification information may correspond to different network slices.

[0007] In the aforementioned solution, after a forwarding path is determined, in other words, after a target interface is determined, one or more interface resource objects on the target interface for forwarding are indicated using the first identification information on the forwarding plane. Furthermore, there is actually only one path between two network devices. However, in the forwarding plane, different service flows actually correspond to different transmission paths. In this way, the topology path calculation result is reused and the waste of interface resources is reduced. The target interface may be a binding interface, and the interface resource object is a physical interface. In this case, the data packet is not forwarded by randomly selecting a subinterface, but the first identification information is used to identify one or more interfaces to be used to forward the data packet. That is, multiple transmission paths for the data packet are planned based on all interfaces between two network devices to improve interface resource utilization.

[0008] The target interface may be a physical interface, and the interface resource object may be a physical sub-interface. Alternatively, the target interface may be a physical interface, and the interface resource object may be a logical sub-interface or a packet object. In this case, when there is only one physical interface between the network devices, multiple logical sub-interfaces or packet queues can be configured on the physical interface for the network device to improve interface resource utilization. Therefore, there are multiple transmission paths between the two network devices. During forwarding path calculation in the control plane, the forwarding path can be determined based only on the physical interface. In the forwarding plane, different service flows actually correspond to different transmission paths. In this way, the topology path calculation result is reused, and the waste of interface resources is reduced.

[0009] In a possible embodiment, the first network device can determine a target interface based on a destination address in the following manner: the first network device determines a target interface identifier corresponding to the destination address based on a correspondence relationship between the destination address and the target interface identifier included in a routing and forwarding table, the target interface identifier being used to identify the target interface.

[0010] In a possible embodiment, the first network device can determine at least one interface resource object on the target interface based on the first identification information in the following manner, that is, the first network device determines a first interface resource object corresponding to the first identification information based on a one-to-one mapping relationship between the first identification information and the first interface resource object on the target interface. In the above embodiment, there is a one-to-one mapping relationship between the first identification information and the first interface resource object, and different service flows are forwarded using different interface resource objects. That is, in order to implement separation between the transmission paths of different service flows, a one-to-one mapping relationship between the first identification information and the first interface resource object is determined based on the one-to-one mapping relationship between the first identification information and the first interface resource object on the target interface. Multiple Different service flows are sent to next-hop network devices by using transmission paths.

[0011] In the scenario of application to network slices, different interface resource objects may be used by different network slices. A target interface between two network devices corresponds to multiple interface resource objects, and different interface resource objects may be used by different network slices. By using the first identification information, the interface resource objects are distinguished, i.e., different network slices are distinguished. After different routes are calculated by using the Flex-Algo ID, the data plane forwarding resources between different network slices are separated on the forwarding plane by using the first identification information. Furthermore, there is actually only one route between two network devices. However, in the forwarding plane, different data actually corresponds to different transmission paths. In this way, the topology path calculation results are reused, and resource waste is reduced.

[0012] In a possible embodiment, the first network device stores a first mapping and forwarding table, and the first mapping and forwarding table includes a correspondence relationship between an identifier of the first interface resource object and each of the target interface identifier and the first identification information. Furthermore, the first network device can determine a first interface resource object corresponding to the first identification information based on the mapping relationship in the following manner: the first network device determines an identifier of a first interface resource object corresponding to the first identification information and located on a target interface identified by the target interface identifier based on the first mapping and forwarding table. The identifier of the first interface resource object is used to identify the first interface resource object.

[0013] In a possible embodiment, a first per-hop behavior (PHB) is used when a first interface resource object is used to forward a service flow, and the first network device forwarding a first data packet to a second network device by using at least one interface resource object includes the first network device forwarding the first data packet to the second network device by using the first PHB and the first interface resource object after determining a first interface resource object corresponding to the first identification information based on a mapping relationship.

[0014] In a possible form, there is a mapping relationship between the first identification information and N interface resource objects, where N is an integer greater than 1, and the first network device determining at least one interface resource object on the target interface based on the first identification information includes the first network device determining M interface resource objects to be used for forwarding the service flow to which the first data packet belongs, from the N interface resource objects to which the first identification information is mapped, where M is a positive integer less than or equal to N.

[0015] In the above embodiment, the M interface resource objects to be used for forwarding the service flow to which the first data packet belongs are mapped with the first identification information. N pieces For example, the M interface resource objects to be used for forwarding the service flow to which the first data packet belongs may be determined from a plurality of interface resource objects to which the first identification information is mapped based on the traffic of the service flow and the bandwidths corresponding to the N interface resource objects, respectively, so as to ensure the quality of service for forwarding the service flow and improve the flexibility for forwarding the service flow.

[0016] For example, when the above embodiment is applied to a network slice scenario, different values ​​of the first identification information correspond to different network slices. The different network slices may be respectively mapped to one or more interface resource objects in the plurality of interface resource objects on the first network device and the second network device. To improve resource utilization, the same interface resource object may be shared by two or more network slices.

[0017] In a possible form, before forwarding the data packet, the first network device receives a mapping relationship between an identifier of the network slice and the first identification information and a mapping relationship between at least one interface resource object in a target interface on the first network device and the first identification information, the at least one interface resource object may be used by a network slice identified by the network slice identifier to which the at least one interface resource object is mapped.

[0018] In a possible embodiment, a PHB used to forward the service flow is configured for each of the N interface resource objects, and forwarding the first data packet to the second network device by using at least one interface resource object by the first network device includes, after determining the M interface resource objects to be used to forward the service flow to which the first data packet belongs, forwarding the service flow to which the first data packet belongs by using the PHB configured for each of the M interface resource objects and the M interface resource objects. A PHB is configured for each interface resource object corresponding to each value of the first identification information. To improve resource utilization, the same interface resource object may be shared by two or more service flows, and the same interface resource object may use different PHBs for different service flows.

[0019] In a possible embodiment, for example, the first identification information corresponds to two interface resource objects. In other words, N is 2, and the first identification information corresponds to a primary interface resource object and a secondary interface resource object. The first network device can determine M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped in the following manner: if it determines that the bandwidth of the primary interface resource object meets the traffic requirement of the service flow to which the first data packet belongs, the first network device determines that the primary interface resource object should be used for forwarding the service flow to which the first data packet belongs.

[0020] Alternatively, if it is determined that the bandwidth of the primary interface resource object does not meet the traffic requirements of the service flow to which the first data packet belongs, the first network device determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs.

[0021] In a possible embodiment, the second PHB is used when the primary interface resource object is used to forward the service flow, and the third PHB is used when the secondary interface resource object is used to forward the service flow, and the first network device forwarding the first data packet to the second network device by using at least one interface resource object may be: the first network device forwarding the first data packet to the second network device by using the second PHB and the primary interface resource object if it determines that the primary interface resource object should be used to forward the service flow to which the first data packet belongs, or the first network device forwarding the first data packet to the second network device by using the second PHB and the primary interface resource object if it determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs. primary The method includes forwarding the first data packet to the second network device by using the interface resource object, or forwarding the first data packet to the second network device by using a third PHB and a secondary interface resource object.

[0022] In a possible embodiment, the second PHB is any one of Expedited Forwarding (EF), Class Selector (CS), Assured Forwarding (AF), and Best Effort (BE), or the third PHB is any one of EF, CS, AF, and BE.

[0023] For example, if the first network device determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs, the second PHB is EF and the third PHB is AF, or the second PHB is EF and the third PHB is BE.

[0024] In the above embodiment, if the traffic of a service flow is larger than the traffic of an interface resource object, the strict prioritized forwarding is used for most of the traffic, and the service level is reduced for the remaining part of the traffic, after which the remaining part of the traffic may be forwarded by using the interface resource object shared with other service flows to improve resource utilization.

[0025] In possible embodiments, the first network device can obtain the first data packet in the following manner: in one embodiment, the first network device receives the first data packet from a previous hop network device of the first network device; in another embodiment, the first network device receives the first data packet from a terminal device; in this embodiment, the first network device may be a head-end network device in a forwarding path of the first data packet, or may be an intermediate network device in a forwarding path of the first data packet.

[0026] In a possible embodiment, when the first network device is a head-end network device in a forwarding path of the first data packet, the first network device can acquire the first data packet in the following manner: the first network device receives a second data packet, where the second data packet is associated with the first network slice, and then the first network device inserts the first identification information into the second data packet based on the correspondence between the identifier of the first network slice and the first identification information to acquire the first data packet.

[0027] In one possible embodiment, the target interface is a binding interface, and the binding interface is configured to establish a neighbor relationship between the first network device and the second network device.

[0028] In one possible embodiment, the packet header of the first data packet includes the first identification information. For example, the packet header of the first data packet includes an extended tag length value (TLV), and the extended TLV includes the first identification information. In another example, the first identification information is included in the packet header of the first data packet as an entropy label.

[0029] In one possible embodiment, the packet header of the first data packet includes a destination address, and the first identification information occupies K bits in the destination address, where K is a positive integer, e.g., the K bits are the K consecutive least significant bits in the destination address, or the K bits are the K consecutive most significant bits in the destination address.

[0030] In one possible embodiment, a packet header of the first data packet includes a traffic class field, and the traffic class field includes the first identification information.

[0031] In one possible embodiment, a packet header of the first data packet includes a flow label, the flow label including the first identification information.

[0032] According to a second aspect, an embodiment of the application further provides a data packet transmission control method, which includes: when creating a first network slice, the controller creates a mapping relationship between an identifier of the first network slice and a first identification information and a mapping relationship between at least one interface resource object in a target interface on the first network device and the first identification information, where the first network slice is capable of using the at least one interface resource object; and the controller sends the mapping relationship between the identifier of the first network slice and the first identification information and the mapping relationship between the at least one interface resource object and the first identification information to the first network device.

[0033] In one example, the value of the first identification information has a one-to-one correspondence with the interface resource object, i.e., different network slices occupy only one interface resource object. In another example, one value of the first identification information may correspond to multiple interface resource objects. Different network slices correspond to different values ​​of the first identification information, and different network slices share the interface resource object.

[0034] In one possible embodiment, the controller configures a PHB for at least one interface resource object to which the first identification information is mapped, for example, the controller configures different PHBs for the same interface resource object to which different values ​​of the first identification information are mapped.

[0035] In one possible embodiment, the target interface is a physical interface; and ,inThe interface resource object may be a physical sub-interface, a logical sub-interface, or a packet queue, or the target interface may be a binding interface and the interface resource object may be a physical interface.

[0036] According to a third aspect, an embodiment of the application provides a data packet transmission control method, comprising: a first network device obtaining a first data packet, the first data packet carrying routing information and first identification information; the first network device determining a target interface based on the routing information, the target interface being an interface present on the first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device; the first network device determining at least one interface resource object on the target interface based on the first identification information; and the first network device forwarding the first data packet to the second network device by using the at least one interface resource object.

[0037] In one possible form, the routing information is a destination address.

[0038] In one possible embodiment, a packet header of the first data packet includes a destination address and the first identification information.

[0039] In one possible embodiment, a packet header of the first data packet includes an extended tag length value (TLV), the extended TLV including a destination address and the first identification information.

[0040] In one possible embodiment, the first identification information is included in a packet header of the first data packet as an entropy label.

[0041] In one possible embodiment, a packet header of the first data packet includes a destination address, the destination address including routing information and the first identification information.

[0042] In a possible form, the routing information occupies the most significant bits in the destination address and the first identification information occupies the least significant bits in the destination address, or the routing information occupies the least significant bits in the destination address and the first identification information occupies the most significant bits in the destination address.

[0043] In one possible embodiment, a packet header of the first data packet includes a destination address and a traffic class field, the traffic class field including the first identification information.

[0044] In one possible embodiment, a packet header of the first data packet includes a destination address and a flow label, the flow label including the first identification information.

[0045] According to a fourth aspect, an embodiment of this application provides a data transmission control device. The device is applied to the first network device in the first aspect or the third aspect. That is, the device may be the first network device, or may be a chip that can be applied to the first network device. The device has a function of implementing each embodiment of the first aspect, or has a function of implementing each embodiment of the third aspect. The function may be performed by hardware, or may be implemented by hardware by executing corresponding software. The hardware or software includes one or more modules corresponding to the function.

[0046] According to a fifth aspect, based on the same inventive concept as the inventive concept of the method embodiment provided in the second aspect, an embodiment of this application provides a data transmission control device. The device is applied to the controller in the second aspect. That is, the device may be a controller or a chip that can be applied to the controller. The device has a function for implementing each embodiment of the second aspect. The function may be performed by hardware, or may be implemented by hardware by executing corresponding software. The hardware or software includes one or more modules corresponding to the function.

[0047] According to a sixth aspect, an embodiment of the present application provides a network device including a processor and a communication interface. The communication interface is configured to receive a communication message. The processor communicates with the communication interface and executes the data transmission control method in any one of the first aspect or the implementation methods of the first aspect or the data transmission control method in any one of the implementation methods of the third aspect by using the communication message received by the communication interface. Optionally, the network device further includes a memory. The memory is configured to store instructions. When the network device is started, the processor executes the instructions stored in the memory, whereby the network device executes the data transmission control method in any one of the first aspect or the implementation methods of the first aspect, or the network device executes the data transmission control method in any one of the implementation methods of the third aspect or the implementation methods of the third aspect. It should be noted that the memory may be located outside the network device. In addition, when the memory is located in the network device, the memory may be integrated into the processor or may be independent of the processor. The network device may further include a memory. The processor is coupled to the communication interface by using a bus. The memory may include readable memory and random access memory.

[0048] According to a seventh aspect, an embodiment of the present application provides a controller including a processor and a communication interface. The communication interface is configured to receive a communication message. The processor communicates with the communication interface and performs the data transmission control method in any one of the second aspect or the implementation methods of the second aspect by using the communication message received by the communication interface. Optionally, controller The method further includes the step of: storing instructions in a memory configured to store instructions in a memory; controller When activated, the processor executes instructions stored in the memory, thereby controller executes the data transmission control method according to the second aspect or any one of the implementation methods of the second aspect. controller It should be noted that the memory may be located outside of the controller If located within the processor, the memory may be integrated into the processor or may be separate from the processor. controller The communication interface may further include a bus. The processor is coupled to the communication interface by using the bus. The memory may include a readable memory and a random access memory.

[0049] According to an eighth aspect, an embodiment of this application further provides a system including an apparatus according to the fourth aspect and an apparatus according to the fifth aspect, or including a network device according to the sixth aspect and a controller according to the seventh aspect. In a possible form, the system may further include another network device interacting with the two network devices in the solution provided in the embodiment of this application, for example another network device in the transmission path, i.e. a second network device.

[0050] According to a ninth aspect, an embodiment of the present application further provides a readable storage medium. The readable storage medium stores a program or instruction. When the program or instruction is executed on a computer, the data transmission control method in any one of the above aspects is performed.

[0051] According to a tenth aspect, an embodiment of the present application further provides a computer program product comprising instructions, which, when executed on a computer, cause the computer to execute the data transmission control method in any one of the preceding aspects.

[0052] In addition, for technical effects provided by any of the third to ninth aspects, please refer to the technical effects provided by different implementations of the first and second aspects, and will not be described in detail here. [Brief description of the drawings]

[0053] [Figure 1] FIG. 1 is a schematic architecture diagram of a network system according to an embodiment of the present application. [Diagram 2] FIG. 1 is a schematic architecture diagram of differentiated services according to an embodiment of the present application. [Diagram 3] 1 is a schematic structural diagram of an IPv4 packet according to an embodiment of the present application. [Figure 4] 1 is a schematic structural diagram of an IPv6 packet according to an embodiment of the present application. [Diagram 5] FIG. 2 is a schematic structural diagram of an ISIS FAD Sub-TLV according to an embodiment of this application; [Figure 6] 1 is a schematic flowchart of creating a network slice according to an embodiment of the present application; [Figure 7] 1 is a schematic diagram of a slice TLV format according to one embodiment of the present application; [Figure 8] FIG. 2 is a schematic structural diagram of a Flex-Algorithm sub-TLV according to an embodiment of this application; [Figure 9] 1 is a schematic structural diagram of an SDGP-ID sub-TLV according to an embodiment of this application; [Figure 10] FIG. 1 is a schematic diagram of a forwarding path corresponding to a network slice according to one embodiment of this application. [Figure 11] FIG. 2 is a schematic diagram of a mapping relationship between SDGP-ID and sub-interfaces according to an embodiment of the present application; [Figure 12] FIG. 2 is a schematic diagram of a data packet forwarding procedure according to an embodiment of the present application; [Figure 13] FIG. 2 is a schematic structural diagram of an IPv6 packet carrying an SDGP-ID according to an embodiment of the present application. [Figure 14] FIG. 2 is a schematic structural diagram of an IPv4 packet carrying an SDGP-ID according to an embodiment of the present application. [Figure 15] FIG. 2 is a schematic structural diagram of an MPLS packet according to an embodiment of this application; [Figure 16] FIG. 2 is a schematic diagram of a SDGP-ID based packet forwarding process according to an embodiment of this application; [Figure 17A] FIG. 2 is a schematic structural diagram of a destination address in an IPv6 packet according to an embodiment of the present application; [Figure 17B] 1 is a schematic structural diagram of an IPv6 packet according to an embodiment of the present application. [Figure 18] FIG. 1 is a schematic structural diagram of an SID in an SRv6 packet according to an embodiment of the present application. [Figure 19] FIG. 2 is a schematic structural diagram of an SRv6 packet according to an embodiment of the present application; [Figure 20] FIG. 2 is another schematic structural diagram of an IPv6 packet according to an embodiment of the present application. [Figure 21] FIG. 11 is yet another schematic structural diagram of an IPv6 packet according to an embodiment of the present application. [Figure 22] FIG. 2 is a schematic diagram of a mapping relationship between resource IDs and sub-interfaces according to an embodiment of the present application; [Figure 23] FIG. 2 is another schematic diagram of a data packet forwarding procedure according to an embodiment of the present application; [Figure 24] 19 is a schematic structural diagram of an apparatus 1900 according to an embodiment of the present application. [Diagram 25] FIG. 20 is a schematic structural diagram of a network device 2000 according to an embodiment of the present application. [Figure 26] FIG. 21 is a schematic structural diagram of a network device 2100 according to an embodiment of the present application. [Figure 27] 22 is a schematic structural diagram of an apparatus 2200 according to an embodiment of the present application. [Figure 28] FIG. 23 is a schematic structural diagram of a controller 2300 according to an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0054] The embodiment of the present application may be applied to a network system including a controller and network devices, as shown in FIG. 1. The network devices may be referred to as nodes, and are devices that provide routing and forwarding functions in the network system. For example, the network devices may be routers, switches, forwarders, or label switching routers (LSRs). This is not limited. In FIG. 1, for example, the network system includes eight network devices, A, B, C, D, E, F, G, and H. It should be understood that the number of network devices included in the network system is not limited in the embodiment of the present application.

[0055] Before the embodiments of this application are described in detail, the technical concepts in the embodiments of this application are first explained.

[0056] (1) Network Slicing 5th generation (5 thThe concept of network slice is proposed in the 5G (Fast Grid) mobile communication technology system. One network slice meets the connection and communication service requirements of a specific type of use case or one use case. The whole 5G system includes a large number of network slices that meet different connection capabilities. Currently, three types of network slices are defined in the 3rd Generation Partnership Project (3GPP) protocol: enhanced mobile broadband (eMBB), ultra-reliable low latency communications (uRLLC), and massive machine type connection (mMTC). Each type of network slice is for a specific service type. For example, the eMBB slice type is used for services with high data rate and high mobility. The uRLLC slice can be used to handle communication scenarios with high reliability and low latency. The mMTC slice can be used for services with a large number of devices, a small amount of data, and infrequent access and latency tolerant (e.g., sensor and wearable device services). As users and services have increasingly higher requirements for customization of network services, different network services are further differentiated. With the in-depth research and large-scale commercial deployment of 5G communication networks, the types of network slices may increase significantly in the near future.

[0057] (2) A service level agreement (SLA) is an agreement signed by a user (e.g., an individual, a company, or a neighboring Internet Service Provider (ISP) having a service interaction with the service provider) and the service provider on how the service flow should be treated when transported within the network. SLA includes many aspects such as payment protocols. In SLA, the technical description part is called Service Level Specification (SLS). The focus of SLS is Traffic Conditioning Specification (TCS). TCS describes detailed performance parameters of each service level, such as average rate, peak rate, committed burst size, and maximum burst size. TCS is the main basis for traffic conditioning in Differentiated Services (DiffServ) networks.

[0058] (3)DiffServ is a service model provided for Quality of Service (QoS). When network congestion occurs, the DiffServ model differentially performs traffic regulation and forwarding based on different service level agreements of services to solve the congestion problem. The flexibility and high scalability of IP networks are fully taken into account, and complex service quality guarantees are converted to single-hop operation by using information carried in packets, and no additional signaling interaction is required.

[0059] The basic idea of ​​DiffServ is to classify incoming flows into different types at the edge of the network, combine flows of the same type for unified management, guarantee quality of service parameters such as the same transmission rate, latency, and jitter, and treat each type of flow separately in the network. Service classification and convergence are performed by edge nodes in the network. Data packets are first identified by their service type, which is recorded in the packet header field. The packets are then sent to the network based on a certain traffic conditioning policy. Internal nodes in the network check the packet header to decide how the packets are to be processed. Figure 2 shows an example of a DiffServ network model. In Figure 2, network nodes configured to implement DiffServ functionality are called Differentiated Service (DS) nodes. DS nodes can be classified into DS boundary nodes and DS internal nodes according to their functions. DS boundary nodes are nodes responsible for connecting other DS domains and domains without DS functionality. DS boundary nodes are responsible for classifying service flows entering a DS domain and performing possible traffic conditioning for the service flows. A DS internal node is configured to connect to DS border nodes and other internal nodes in the same DS domain. A DS internal node only needs to perform simple flow classification based on Differentiated Services Code Point (DSCP) values ​​and perform traffic conditioning for the corresponding flows. A DS Domain includes a group of connected DS nodes that use the same service provisioning policy and enforce the same Per Hop Behavior (PHB). A DS Domain includes one or more networks of the same administrative department. A DS Domain may be an ISP or an enterprise intranet.

[0060] (4) PHB may also be referred to as hop-by-hop operation. Different PHBs may be represented using different DSCP values ​​in IPv4 and IPv6 packets. The DSCP value is placed in the type of service (ToS) field in the IPv4 packet header and in the traffic class (TC) field in the IPv6 packet header.

[0061] FIG. 3 shows an example of an IPv4 packet format. The Version field of an IPv4 packet indicates the IP version number of the data packet. The Header Length field indicates the length of the packet header of the data packet. The Total Length field indicates the total length of the data packet and can be used to calculate the length of the payload in the data packet. The Identification field has a length of 16 bits and is usually used for data packet fragmentation with a flag field and a fragment offset field. If the original length of the data packet exceeds the maximum transmission unit (MTU) of the data link through which the data packet will pass, the data packet needs to be fragmented into smaller data packets. For example, when a 5000-byte data packet passes through a network, if there is a data link with an MTU of 1500 bytes, i.e., a data frame can accommodate a data packet with a maximum of 1500 bytes, the node needs to fragment the data packet into multiple data packets before the data is framed, and the length of each data packet should not exceed 1500 bytes. The router then marks the identification field of all data packets with the same mark so that the receiving device can identify the fragments that belong to the same data packet. The IP Flags field has a length of 3 bits, and the first bit is unused. The second bit is the Don't Fragment (DF) bit, and the router cannot fragment the data packet after the second bit is set to 1. If the data packet exceeds the MTU value, the router cannot forward the data packet, but discards the data packet and sends an error message to the sender. The Fragment Offset field has a length of 13 bits and is used to indicate the offset of the fragment start point relative to the header start point.Fragments may arrive out of order, and the Fragment Offset field may enable the receiver to reassemble the data packet in the correct order. The Time To Live field is 8 bits long and is used to indicate the number of hops for transmission. The Protocol field is 8 bits long and indicates the protocol number of the data packet. The Header Checksum field is an error correction field in the IP packet header. The Source Address field and the Destination Address field represent the IP addresses of the source node and the destination node of the data packet, respectively. There is an Options field, whose data portion is the data to be carried in the data packet.

[0062] FIG. 4 shows an example of the format of an IPv6 packet. The Version of an IPv6 packet represents the IP version number of the data packet. The TC field is used to distinguish services and is used to identify the service type of the data packet. The flow label field is used to mark data packets that belong to the same service flow. The flow label, source address, and destination address together uniquely identify a service flow. All data packets in the same service flow have the same flow label, which makes it easy to process flows with the same QoS requirements. The payload length field contains the byte length of the payload of the data packet. The next header field defines the protocol type in the next extended packet header field following the IPv6 base header. The hop limit field usually has a length of 8 bits. Each time a node forwards a data packet, the value of this field is decreased by 1. When the value of this field reaches 0, the data packet is discarded. The source address and destination address represent the IP address of the source node and the IP address of the destination node of the data packet, respectively.

[0063] A PHB describes the externally visible forwarding behavior used by a DS node for packets with the same DSCP. A PHB can be defined by priority or by some visible service characteristics, such as packet latency, jitter, or packet loss rate. A PHB defines only some of the externally visible forwarding behavior and does not prescribe a specific implementation. Currently, four types of PHBs are defined in the standard protocol: Class Selector (CS), Expedited Forwarding (EF), Assured Forwarding (AF), and Best-Effort (BE). BE is the default PHB.

[0064] The service level represented by CS is the same as the IP precedence used in existing networks. EF is defined as such a forwarding arrangement in which the rate of information flow sent from any DS node in any case must be equal to or greater than a specified rate. EF PHBs cannot be remarked in DS domains, only at border nodes. AF satisfies the following requirements: When a user subscribes to an ISP's bandwidth service, the traffic volume is allowed to exceed the subscribed specification. It is required to ensure the forwarding quality of traffic that does not exceed the subscribed specification. Traffic that exceeds the specification is not simply discarded, but is given a service level. level BE corresponds to traditional IP packet delivery services, focuses only on reachability, and does not impose requirements on other aspects.

[0065] (5) Flexible Algorithm (Flex-Algorithm, Flex-Algo) The Flex-Algorithm is defined in the draft [draft-ietf-lsr-flex-algo]. Currently, the best route can be calculated (may be called route computation) by using an interior gateway protocol (IGP). IGP is a protocol for exchanging routing information between gateways (hosts and routers) in an autonomous network. In an IGP protocol, the best route in a network is calculated based on an IGP metric assigned to the links. Since the IGP metric does not reflect the traffic requirements, the best route calculated based on the IGP metric is usually replaced by a traffic engineered route. Many networks deploy various types of traffic engineering, such as resource reservation protocol-traffic engineer (RSVP-TE) or segment routing-traffic engineering (SR-TE). In this case, the network is forced to calculate the best route based on RSVP-TE or SR-TE using the metric or constraints of the shortest IGP route. The Flex-Algorithm proposes to define a combination of constraints that are flooded in an IGP domain such that nodes in the IGP domain compute constraint-based routes based on the same constraints to implement distributed TE. Each combination of constraints defined in a Flexible-Algorithm can be represented using a Flexible-Algorithm ID. A Flexible-Algorithm ID is a numeric identifier in the range of 128 to 255 that is associated with a Flexible-Algorithm Definition (FAD) through configuration.

[0066] A FAD is a set that includes (a) a calculation type (Calc-Type), (b) a metric type (Metric-Type), and (c) a link constraint.

[0067] Metric-Type identifies the metric type used in the Flex-Algorithm computation process. If Metric-Type is 0, it indicates IGP metric. If Metric-Type is 1, it indicates min unidirectional link delay. If Metric-Type is 2, it indicates TE metric.

[0068] If Calc-Type is 0, it is shortest path first. (S Calc-Type is 1, which indicates strict SPF.

[0069] Link constraints are described using include / exclude admin-group(link color: color). Link color, also called affinity attribute, is a 32-bit vector that represents link attributes. For example, link color can be used to represent link bandwidth, performance, or administrative policies. Links of the same color correspond to the same link attributes. For example, if a link is colored green, then the link attributes of different links colored green are the same.

[0070] For example, the ISIS FAD Sub-TLV is used to carry the contents of the Flex-Algorithm definition. Figure 5 is a schematic structural diagram of the ISIS FAD Sub-TLV. In Figure 5, the Type field identifies the type of the TLV, the Length field represents the byte length of the TLV, the Flex-Algorithm field identifies the Flexible-Algorithm ID value, and the Metric-Type field identifies the Metric type used in the calculation process of the Flexible-Algorithm. The Calc-Type field identifies the calculation model defined for the specified IGP algorithm, and the metric and constraints cannot be inherited. The Priority field ranges from 0 to 255 and identifies the priority for advertising the TLV. The Sub-TLV field is optional. For example, different link attributes (colors) may be set for different links by adding the Exclude Admin Group Sub-TLV, Include-Any Admin Group Sub-TLV, and Include-All Admin Group Sub-TLV to the Sub-TLVs. The Exclude Admin Group Sub-TLV is used to advertise rules that should be excluded during Flex-Algorithm route computation. The Include-Any Admin Group Sub-TLV is used to advertise any rules that should be included during Flex-Algorithm route computation. The Include-All Admin Group Sub-TLV is used to advertise all rules that should be included during Flex-Algorithm route computation.

[0071] Currently, in network slice scenarios, Flexible-Algorithm technology can be used in combination with network slices, and different network slices are distinguished by using Flexible-Algorithm IDs. That is, different constraint attributes are defined for different network slices to forward different service flows to different network slices. When performing path computation based on the algorithm constraints identified by each Flexible-Algorithm ID, the controller side needs to perform path computation based on the algorithm constraints identified by each Flexible-Algorithm ID, calculate forwarding paths, and generate routing tables. Even if different network slices correspond to the same forwarding device, the topology path computation results cannot be reused, resulting in a waste of interface resources.

[0072] In a non-network slicing scenario, a network device may have multiple interfaces configured to communicate with a next-hop network device. In this case, the network device typically randomly selects an interface for forwarding a data packet to a next-hop network device or selects an interface based on the activity state of the interface. As a result, forwarding resources cannot be separated and some interfaces may be idle, thereby resulting in a waste of interface resources.

[0073] Based on this, the embodiments of this application provide a data transmission control method and apparatus. One or more identification information is added to determine an interface resource object for forwarding a data packet on an interface of a network device. The interface of the network device may be a physical interface or a binding interface obtained by combining multiple physical interfaces. The interface resource object may be a physical interface, a physical sub-interface, a logical sub-interface (e.g., a channelized sub-interface or a Flex-E sub-interface), or a packet queue. Different interface resource objects may correspond to different interface forwarding resources.

[0074] In the following example, one identification information is added to determine an interface resource object on an interface of a network device for forwarding a data packet. In an embodiment of this application, one global identification information is added, and the global identification information is used to select an interface resource object on an interface for forwarding a data packet. The global identification information may be called a first identification information, or may be called a self-definition global policy identification (SDGP ID for short). The SDGP ID has a global meaning and is used to select a forwarding resource. Alternatively, the global identification information may be called by another name. This is not limited in the embodiment of this application. In the embodiment of this application, an explanation is given by using an example in which the global identification information is called SDGPID. The controller creates a mapping relationship between different values ​​of SDGPID and one or more interface resource objects. When the same value of SDGP ID corresponds to multiple interface resource objects, the same interface resource object may be selected. S DGP-ID Multiple values ​​ofOf course, it may correspond to one interface resource object. S DGP-ID One value of After creating the mapping relationship between the different values ​​of the SDGPID and one or more interface resource objects, the controller sends the mapping relationship to the network device side. A first network device on the network device side is used as an example. The first network device obtains a first data packet in the service flow, and then determines a target interface based on the destination address carried in the first data packet. The target interface is an interface that exists on the first network device and is configured to connect to a second network device. The second network device is a next-hop network device of the first network device. Then, the first network device receives the first identification information (SDG ID) carried in the first data packet and sends the mapping relationship to the network device side. and determining at least one interface resource object on the target interface based on the first data packet's P-ID, and further forwarding the first data packet to the second network device by using the at least one interface resource object.

[0075] In the embodiment of this application, when the SDGP ID is applied to the network slice technology of the bearer network, it can be defined as follows, that is, different values ​​of the SDGP ID correspond to different network slices. Different network slices correspond to one or more interface resource objects, and one interface resource object may be used by one network slice or may be used by multiple network slices. A scenario of application to a software defined network (SDN) is used as an example. An interface resource object corresponding to a self-defined global policy identifier may be defined by an SDN controller and distributed to the network device side. In the data packet forwarding process, the self-defined global policy identifier is carried in the data packet, and the data packet further carries a destination address. The network device analyzes the data packet and uses the destination address to determine an interface that exists on the network device and is connected to the next-hop network device, and then selects an interface resource object on the interface based on the SDGP-ID to forward the service flow. The data packet in the embodiment of this application is an IPv4 packet. to, It may be, but is not limited to, a multi-protocol label switching (MPLS) packet, or an IPv6 packet.

[0076] In the following description, a network slice application scenario is used as an example.

[0077] In the following, we first use an example where there is a one-to-one mapping relationship between SDGP-ID and interface resource object.

[0078] Figure 6 is a schematic flowchart of distributing the mapping relationship between the SDGP-ID and the interface resource object by the controller in the network slice creation process.

[0079] S601. The controller receives a network slice creation request sent by a slice manager, where the network slice creation request may include network slice requirement information. For example, the network slice requirement information may include parameters such as a network slice name (Network Slicing ID), a network slice type, and SLA requirements. When requesting the creation of a network slice, the slice manager may request to create one network slice at a time, or may request to create multiple network slices at a time.

[0080] S602. The controller creates a network slice based on the network slice requirement information. For example, the controller may include a network slice management module configured to create a network slice based on the network slice requirement information. Specifically, if the network topology created by the controller meets the requirements of the network slice, the controller may assign the network topology to the network slice and configure a multi-topologies (MT) ID or a Flex-Algorithm ID of the network slice. If none of the network topologies created by the controller meets the requirements of the network slice, the controller may create a network topology based on the network slice requirement information and generate an MT-ID or a Flex-Algorithm ID. The controller further needs to configure a self-defined global policy identifier (SDGP ID) of the network slice and assign a corresponding interface resource object to the network slice. Different network slices correspond to different SDGP-IDs. For example, the interface resource object is a sub-interface on a network device. Different sub-interfaces are used as forwarding resources of different network slices, and different sub-interfaces correspond to different self-defined global policy identifiers (SDGP IDs).

[0081] It should be noted that the network topology can be obtained using the Flex-algo technique or the Multi-Topology (MT) technique. The identifier of the network topology obtained using the Flex-algo technique is called the Flex-Algorithm ID, and the identifier of the network topology obtained using the Multi-Topology technique is called the MT-ID.

[0082] In the following description, an example is used in which the network topology is obtained using the Flex-algo technique.

[0083] The network slice configuration model includes a network topology (MT-ID or Flex-Algorithm ID) and a global policy identifier (SDGP-ID). The network slice configuration model is distributed to the network devices by using a controller or by a user-defined configuration method. Each network device can flood the network slice configuration model in the network by advertising the Network-Slicing TLV so that all network devices in the network have the same network slice configuration model for the network slice with the same Network-Slicing ID. The Network Slicing TLV may be a top-level TLV or may be used as a sub-TLV of the TLV currently to be advertised. For example, the Network Slicing TLV may be used as a sub-TLV of the Router capabilities TLV. This is not limited in this embodiment of the application.

[0084] For example, the network slice configuration model may be Network-slicing ID: 1; Flex-Algorithm ID: 128; SDGP-ID: 100

[0085] Figure 7 is a schematic diagram of the format of the Network-Slicing TLV. In Figure 7, Type represents the type of TLV, Length represents the length of the TLV, Flags represents that there is currently no flag bit definition, which is a reserved bit, Network-Slicing-ID represents the network slice identifier, and Optional sub-sub-TLVs represents the sub-TLV type included in the network slice TLV.

[0086] For example, the Optional sub-sub-TLVs may include a Topo sub-TLV / Flex-Algorithm sub-TLV and an SDGP-ID sub-TLV. The Topo sub-TLV / Flex-Algorithm sub-TLV is used to carry a Flex-Algorithm ID, and the SDGP-ID sub-TLV is used to carry an SDGP-ID. Figure 8 is a schematic structural diagram of a Topo sub-TLV / Flex-Algorithm sub-TLV. In Figure 8, Topo ID / Flex-Algorithm ID represents a network topology identifier. Figure 9 is a schematic structural diagram of a SDGP-ID sub-TLV. In Figure 9, Reserved represents a reserved bit.

[0087] S603. The controller sends information about the created network slice to the target network device. The target network device may be understood as a network device determined by the controller based on a network topology corresponding to the network slice. The controller determines a network topology corresponding to the network slice 1, as shown in FIG. 1, where the network topology includes A, B, C, D, E, F, G, and H. The controller can send information about the network slice 1 to an edge network device (e.g., network device A) in the network topology, and then the edge network device (e.g., network device A) can notify the network devices (B, C, D, E, F, G, and H) in the network topology of the information about the network slice 1 in a flooding manner, i.e., the edge network device is the target network device. The controller can send information about the network slice 1 to each network device in the network topology that establishes a connection to the controller. For example, if A, B, C, D, E, F, G, and H are all connected to the controller, the controller can send information about the network slice 1 to A, B, C, D, E, F, G, and H. The information about the network slice includes the network topology, the SDGP-ID, and the correspondence between the SDGP ID and the interface resource object. There may be a one-to-one correspondence between the SDGP-ID and the interface resource object, or one SDGP-ID may correspond to two or more interface resource objects.

[0088] When the forwarding path is calculated based on the network topology, the affinity attribute corresponding to the Flex-Algorithm ID, the metric type, etc., the controller can perform path calculation and send the path calculation result to the head-end network device. Alternatively, the head-end network device can perform path calculation and report the path calculation result to the controller. The network device can assign an adjacent label based on the IGP protocol and report the assigned adjacent label to the controller, so that the controller generates a label stack list used to forward the data packet based on the adjacent label and the path calculation result. After assigning the adjacent label, each network device floods the adjacent label throughout the network, so that each network device in the network knows the adjacent label advertised by another network device using the IGP protocol to determine the next-hop network device when forwarding the data packet.

[0089] The controller or network device calculates forwarding paths for different network topologies separately, i.e., calculates different forwarding paths for different Flex-Algorithm IDs. However, the forwarding paths used by different network slices may be the same, i.e., different network slices reuse the same network topology. Therefore, the controller / network device needs to calculate forwarding paths only once for different network slices of the same network topology. When the controller calculates the forwarding path, the controller may further include a path computation control module. The path computation control module performs path computation based on different network topologies and sends the path computation result to the network slice management module to establish an association between the network slice and the forwarding path obtained by the path computation. The network slice configuration model defines different SDGP-IDs to ensure data separation in the forwarding plane. In FIG. 10, two Flex-Algorithm IDs 128 and 129 are defined, and different metric types are used as path attribute definitions for the two Flex-Algorithm IDs 128 and 129. For Flex-Algorithm ID 128, IGP metric is used as the route computation constraint, and for Flex-Algorithm ID 129, link-delay metric is used as the route computation constraint. Different segment routes are configured for different Flex-Algorithm IDs, and the segment routes are used to distinguish the network topology. It is assumed that two Flex-Algorithm IDs correspond to the same affinity attribute, i.e., the network topology of the two Flex-Algorithm IDs is the same, i.e., all network devices in the network. However, since the metric types for route computation are different, it is possible to distinguish between two Flex-Algorithm IDs for the same link. M The etric types are different, and therefore the route calculation results of the two Flex-Algorithm IDs are different.

[0090] For example, network slices are configured via Segment Routing IPv6 (SRv6).

[0091] For Flex-Algorithm ID 128, the shortest route from node A to node D is calculated using IGP metric, and the route calculation result is A→B→C→D.

[0092] For the definition of Flex-Algorithm ID 128, please see below. Flex-Aglo id 128: Metric: igp-metric Calc-type:0 Link Constraint: Affinity (Affinity Attribute) For example, if the link constraint is green, it indicates that green links are excluded or included when Flex-Algorithm ID 128 is used for route computation.

[0093] For Flex-Algorithm ID 129, the shortest route from node A to node D is calculated using the delay metric, and the route calculation result is A→E→F→G→D.

[0094] For the definition of Flex-Algorithm ID 129, please see below. Flex-Algorithm ID 129: Metric: link-delay-metric Calc-type:0 Link constraint: Affinity. For example, if the link constraint is purple, it indicates that purple links are excluded or included when Flex-Algorithm ID 129 is used for path computation.

[0095] Referring to Figure 10, three network slices are used as an example. Network slice 1:Network Slicing ID:1;Flex-Algorithm ID:128;SDGP-ID:1 Network slice 2:Network Slicing ID:2;Flex-Algorithm ID:128;SDGP-ID:2 Network slice 3: Network Slicing ID: 3; Flex-Algorithm ID: 129; SDGP-ID: 3

[0096] Network slice 1 and network slice 2 use the same Flex-Algorithm ID 128. Therefore, the topologies of network slice 1 and network slice 2 are the same, and the route computation results are the same on the control plane. However, the SDGP IDs are different, and thus data separation can be implemented in the forwarding plane. The Flex-Algorithm ID of network slice 3 is different from that of network slice 1 and network slice 2, and route computation is performed using the delay metric value of network slice 3. Therefore, the route computation results on the control plane are different from the route computation results of network slice 1 and network slice 2 obtained by route computation using the IGP metric.

[0097] S604. The network device, based on the correspondence between the SDGP ID and the interface resource object distributed by the controller, Mapping and Forwarding Generate a table.

[0098] Referring to FIG. 10, the forwarding resources corresponding to the three network slices are indicated by arrows. The three different network slices use different SDGP-IDs, and therefore the interface resource objects identified by the SDGP-IDs are different. The controller determines whether the network device Mapping and ForwardingDistribute the mapping relationship between the SDGP-ID and the interface resource object to the network device to generate a table. For example, the interface resource object is a sub-interface. For example, there are multiple sub-interfaces between network device A and network device B.

[0099] There are multiple sub-interfaces between network device A and network device B. Referring to FIG. 11, three sub-interfaces are used as an example. Mapping and Forwarding A table needs to be established. For example, multiple sub-interfaces can form a binding interface, e.g., a Trunk interface. Specifically, the controller can construct the binding interface by using a Trunk set model. In the Trunk set model, the corresponding sub-interfaces in the binding interface can be indexed based on the attributes (e.g., bandwidth) configured for the sub-interfaces in the binding interface. The Trunk interface operates at layer 3 (layer 3 IP is configured and IGP neighbor relationships are established). The sub-interfaces operate at layer 2 (IP is not configured). The IGP neighbor relationships are established between the network devices based on the Trunk interfaces instead of the actual sub-interfaces. In this case, when there are parallel links between the neighbors, the number of neighbors that need to be maintained using an IGP routing protocol can be reduced. The IGP neighbor relationships are established based only on the Trunk interfaces, e.g., the IGP neighbor relationships established based on the Trunk interfaces in FIG. 11. In the forwarding plane of the network device A, Mapping and Forwarding The table is generated and maintained based on the relationship between the sub-interfaces and each Trunk interface and the SDGP-ID, as shown in Table 1.

[0100] [Table 1]

[0101] It should be understood that the identifiers of the Trunk interfaces configured between different network devices are different. For example, the Trunk interface between network device A and network device B may be called the Trunk0 interface and have an identifier A. For example, the Trunk interface between network device A and network device E may be called the Trunk1 interface and have an identifier B. When distributing information about the network slice to the network device, the controller may notify the network device of the identifier of the Trunk interface and the sub-interfaces included in the Trunk interface indicated by the identifier of the Trunk interface.

[0102] In one example, the SDGP-ID and the sub-interface are not limited to a one-to-one correspondence, and one SDGP-ID may correspond to two or more sub-interfaces. During the forwarding of the service flow, the service flow may be forwarded in an offload manner, that is, the service flow is forwarded using multiple sub-interfaces corresponding to the SDGP-ID.

[0103] When the SDGP-ID has a one-to-one correspondence with the interface resource object, the procedure for forwarding a service flow by a network device is shown in FIG.

[0104] S1201. A first network device obtains a first data packet, the first data packet carrying a destination address and first identification information, the first data packet being any data packet in a service flow.

[0105] S1202. A first network device determines a target interface based on a destination address, the target interface being an interface present on the first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device.

[0106] In a network topology, there may be multiple network devices connected to a first network device, and the first network device is connected to different network devices via different interfaces. The first network device can use the destination address to determine a next-hop network device (i.e., a second network device) for forwarding the service flow, i.e., the target interface is an interface present on the first network device and configured to connect to the second network device.

[0107] For example, when determining a target interface based on a destination address, the first network device may determine a target interface identifier corresponding to the destination address based on a routing and forwarding table, and the target interface identifier is used to identify the target interface to determine the target interface. The routing and forwarding table includes a correspondence between the destination address and the target interface identifier. The target interface identifier indicates a next-hop network device in a forwarding path of the first data packet.

[0108] S1203. The first network device determines a first interface resource object on the target interface based on the first identification information.

[0109] For example, there is a one-to-one mapping relationship between the first identification information and the first interface resource object on the target interface. The mapping relationship may be stored in the first network device so that the first network device can determine the first interface resource object on the target interface based on the first identification information. For example, there are multiple interface resource objects on the target interface. For example, the target interface is a binding interface. The binding interface includes multiple sub-interfaces, and the interface resource object is the sub-interface. In this case, the first network device determines a sub-interface to which the first identification information is mapped from the multiple sub-interfaces included in the binding interface to forward the first data packet.

[0110] When storing the one-to-one mapping relationship between the first identification information and the first interface resource object in the target interface, the first network device may store the mapping relationship in the form of a table. For example, the first network device may store the one-to-one mapping relationship between the first identification information and the first interface resource object in the target interface. Mapping and Forwarding In this case, the first Mapping and Forwarding The table includes a correspondence between the identifier of the first interface resource object and each of the target interface identifier and the first identification information, so that the first network device can Mapping and Forwarding Based on the table, an identifier of a first interface resource object that corresponds to the first identification information and exists on the target interface identified by the target interface identifier is determined, and the identifier of the first interface resource object is used to identify the first interface resource object for further determining the first interface resource object.

[0111] S1204. The first network device forwards the first data packet to the second network device by using the first interface resource object.

[0112] The first network device may be a head-end network device in the forwarding path of the service flow, or may be an intermediate network device in the forwarding path, which is not limited in this embodiment of the present application.

[0113] If the first network device is an intermediate network device, the data packet received by the first network device from the previous hop network device carries the first identification information. If the first network device is a head-end network device, the data packet received from the terminal device can carry the first identification information. That is, the first identification information may be transmitted to the first network device by appending the first identification information to the data packet when the terminal device transmits the data packet. Alternatively, the data packet transmitted by the terminal device may not carry the first identification information. In this case, when the first network device functioning as a head-end network device receives a second data packet from the terminal device, the second data packet does not carry the first identification information. When determining that the second data packet is associated with the first network slice, the first network device inserts the first identification information into the second data packet based on the correspondence between the identifier of the first network slice and the first identification information to obtain the first data packet. The correspondence between the identifier of the first network slice and the first identification information may be created by the controller when the network slice is created and distributed to the first network device. In addition, mutual access between different services may be separated by using the first identification information extended on the data plane. The network device at the entrance of the forwarding path encapsulates the identification when receiving a packet and checks the identification when the packet is sent from the intermediate network device. This improves the risk resistance capability and security guarantee of the network. For example, when an attack packet is generated, most of the attack packet can be eliminated by interface packet checking.

[0114] The first identification information may be carried in a packet header of the first data packet. The first identification information may be carried in the packet header of the first data packet in multiple ways. Some ways are described below as examples.

[0115] In the first method, both the first identification information and the destination address are carried as two pieces of information in a packet header of the first data packet.

[0116] For example, the first identification information may be carried in an extended TLV or a sub-TLV. The first data packet may be an IPv6 packet, an IPv4 packet, a multi-protocol label switching (MPLS) packet, or another type of packet, which is not limited in this embodiment of the application.

[0117] In one example, the first data packet is an IPv6 packet, and the first identification information (i.e., SDGP-ID) may be carried in an IPv6 hop-by-hop option header of the iPv6 data packet. Figure 13 is a schematic structural diagram of a packet header of an iPv6 data packet carrying SDGP-ID. A newly added TLV type is used in an extension header of the packet header to carry SDGP-ID. In Figure 13, Next Header represents the protocol type of the next packet header, Header Ext Len represents the length of the extension header (excluding the bytes occupied by Next Header), Type identifies the option type, and the corresponding following type-specific data field carries SDGP-ID, and Length represents the data length of SDGP-ID.

[0118] In another example, the first data packet is an IPv4 packet. Referring to the structure of the IPv4 packet shown in FIG. 3, the first identification information (i.e., SDGP-ID) may be carried in an Options field of the IPv4 packet header. A self-defined TLV type may be used for Options of the IPv4 packet. Referring to FIG. 14, the self-defined TLV includes Type, Length, and SDGP-ID. Type is used to identify the type of the option field, Length indicates the length of the self-defined TLV, and SDGP-ID is used to indicate the interface resource object used to forward the data packet.

[0119] In yet another example, the first data packet is an MPLS packet, and the first identification information (i.e., SDGP-ID) may be carried in the MPLS packet as an entropy label. Figure 15 shows an example of a format of an MPLS packet carrying an SDGP-ID. In Figure 15, ETH indicates a layer 2 Ethernet packet header. l The label / VPN label / MPLS label is used to identify the outbound interface or the next hop of the forwarding path. The reserved label is used to identify that the lower layer label of the reserved label is a network slice label. Each hop of the network device accesses the SDGP label, identifies the label value of the SDGP label, i.e., the SDGP-ID value, queries the interface resource object identified by the SDGP-ID, and forwards the MPLS packet.

[0120] In one example, referring to FIG. 16, the forwarding path is network device A→network device B→network device C. There are three subinterfaces in each of network device A, network device B, and network device C, namely subinterface 0 (interface 0), subinterface 1 (interface 1), and subinterface 2 (interface 2). It should be understood that the naming method of subinterfaces of the same attribute (e.g., bandwidth) on different network devices may be the same or may indeed be different. In FIG. 16, the same naming method is used as an example. On each network device, subinterface 0, subinterface 1, and subinterface 2 form a binding interface, e.g., Trunk0. Subinterface 0 is the forwarding resource of network slice 1, subinterface 1 is the forwarding resource of network slice 2, and subinterface 2 is the forwarding resource of network slice 3. Subinterface 0 corresponds to SDGP-ID 1, subinterface 1 corresponds to SDGP-ID 2, and subinterface 2 corresponds to SDGP-ID 3. For example, network device A receives data packet 1, and searches the routing and forwarding table based on the destination address A in the data packet 1 to determine the binding interface. For example, the destination address A corresponds to outbound Trunk 0 in the routing and forwarding table. Then, network device A uses the forwarding resource of network slice 1, i.e., sub-interface 0, to forward data packet 1 to network device B based on the outbound Trunk 0 and SDGP-ID in data packet 1 (for example, the SDGP-ID carried in data packet 1 is SDGP-ID 1). Network device B Similarly, determines to forward data packet 1 to network device C using sub-interface 0.

[0121] In one example, the interface resource object corresponding to the SDGP-ID may be further associated with a PHB used to forward the service flow. Thus, when forwarding a data packet using an interface resource object determined using the SDGP-ID, the first network device forwards the data packet using a forwarding behavior indicated by the PHB associated with the interface resource object corresponding to the SDGP-ID. The network device may further add the PHB used by the interface resource object corresponding to the SDGP-ID to the forwarding table through mapping, or may securely store the PHB in an independent table or another non-table manner. This is not particularly limited in this application.

[0122] In a second method, the first identification information can reuse the destination address field, and the first identification information is carried in the packet header of the first data packet as part of the destination address.

[0123] In one example, an IPv6 packet is used, and the first identification information (SDGP-ID) is extended into the destination address (DA) field of the IPv6 packet header. The position of the SDGP-ID in the DA field is not limited in this embodiment of this application. For ease of explanation, the information used to determine the target interface in the destination address is called routing information. For example, the SDGP-ID may be adjacent to the routing information, or of course, may not be adjacent to the routing information, and the SDGP-ID may be part of the routing information. For example, the routing information is located in the most significant bit in the DA field, and the first identification information is located in another bit. Indeed, the first identification information may alternatively be located in the most significant bit in the DA field, and the routing information may be located in the least significant bit.

[0124] For example, as shown in Figures 17A and 17B, an IPv6 DA is 128 bits, and some bits in the DA are defined to identify an SDGP-ID.

[0125] The forwarding path shown in Figure 10 is used as an example. For example, the routing table maintained locally by network device A is shown in Table 2.

[0126] [Table 2]

[0127] For example, the 16 least significant bits in the destination address are the SDGP-ID. Network device A receives a first data packet, and the DA in the first data packet is c0a8:2048::2. If c0a8:2048:: / 32 matches based on the longest IP match rule, the corresponding outbound interface is the outbound interface from A to B, that is, the Trunk0 interface. The least significant bits of the 128 bits within the 16 bits of the DA are defined to identify the SDGP-ID, for example, the value of the least significant bit of the 16 bits of c0a8:2048::2 is 2. Therefore, Mapping and Forwarding The table is queried based on SDGP-ID 2. For example, as shown in Table 3, the sub-interfaces in the Trunk0 interface S2 That is, the first data packet is forwarded to network device B using sub-interface 2.

[0128] [Table 3]

[0129] As another example, a segment routing over IPv6 forwarding scenario is used. For example, an IPv6 DA is an SRv6 SID defined in SRv6. Similarly, the above-mentioned method can be used, and K bits of the extended SRv6 SID format are used to identify the SDGP-ID. Figure 18 shows an example of the structure of an SRv6 SID. Locator has a location function. Function indicates the device's command and is used to indicate the node that generates the SRv6 SID to perform the corresponding function operation. Arguments is an optional parameter field and is used to define information such as the flow of packets and services. For example, the SDGP-ID may be information in the Argument, or may be K bits independent of the Argument.

[0130] Figure 19 shows an example of the structure of an SRv6 data packet. Next Header indicates the type of packet header immediately following the SRH. Hdr Ext Len indicates the length of the SRH header, which is mainly occupied by Segment List [0]~SegmentList [n]. Routing Type is used to indicate the route header type. SRH Type is 4. Segments Left (SL) indicates the number of intermediate nodes to be accessed before reaching the destination node. Last Entry indicates the index of the last element of the segment list. Flags indicates some flags of the data packet. Tag identifies packets in the same group. Segment List [n] indicates the segment list. Segment List is encoded from the last segment of the route. Segment List is in the format of an IPv6 address. Segment List [n] is the first segment list processed in the SRv6 route, Segment List [n-1] is the second segment list processed, and Segment List [n- 2] is the third segment list to be processed, ...Segments List [0] is the n+1th segment list to be processed. Each time through an SRv6 node, the Segments Left (SL) field is decremented by one and the IPv6 DA information is changed once. The Segments Left and Segments List fields together determine the IPv6 DA information. If the SL value is n (n-0), the IPv6 DA value is the value of Segments List [n]. If the SL value is n-1, the IPv6 DA value is the value of Segments List [n-1]. Analogically, if the SL value is 1, the IPv6 DA value is the value of Segments List [1]. If the SL value is 0, the IPv6 DA value is the value of Segments List [0].

[0131] If the SRv6 SID is not the SID of the local node, the SRv6 SID is a generic IPv6 DA, and in the above example where the first identity reuses the destination address in the IPv6 packet, the packet is forwarded in a forwarding manner. If the SRv6 SID is the SID of the local node, the information about the outbound interface / next hop is stored in the forwarding information base (FIB) table (and / or the routing table), Mapping and Forwarding The interface is found by querying a table or the like, and then the sub-interface is determined based on the SDGP-ID information carried.

[0132] In one example, SRv6 data is forwarded based on End SID and End.X SID. End SID stands for Endpoint SID, is used to identify a destination address prefix in the network, is globally visible and is globally valid in the system. End.X SID stands for Endpoint SID of layer 3 cross-connect, is used to identify a link in the network, is globally visible and is locally valid.

[0133] After receiving an SRv6 data packet, the node first queries the local SID table based on the destination address (SRv6 SID) to determine whether the SRv6 SID corresponding to the destination address is an End SID or an End.X SID. If the SRv6 SID is an End SID, the node continues to query the FIB table (and / or routing table), queries the target interface corresponding to the SRv6 SID based on the IPv6 FIB table, and queries the target interface corresponding to the SRv6 SID based on the SDGP-ID in the SRv6 SID. Mapping and Forwarding The subinterface is determined by querying the table, and then the determined subinterface is used to forward the data packet. If the SRv6 SID is an End.X SID, the next hop (outbound interface) of the SRv6 SID is determined without querying the FIB table, Mapping and Forwarding The table is queried based on the SDGP-ID in the SRv6 SID to determine the sub-interface, and then the data packet is forwarded using the determined sub-interface.

[0134] In a third method, the first identification information may reuse another field in the packet header of the first data packet, such as a traffic class (TC) field, a flow label field, or a source address field.

[0135] In one example, an IPv6 packet is used, and the first identification information reuses the traffic class field. All or part of the traffic class field may be used to indicate the first identification information. For example, referring to FIG. 20, all of the traffic class field is used to indicate the first identification information. Traffic class The position of the first identification information in the field and the number of bits occupied by the first identification information are not particularly limited in this embodiment of the application.

[0136] After the first network device obtains the first data packet, the first network device determines a target interface based on a destination address in a packet header of the first data packet, then obtains first identification information from a traffic class field of the packet header, determines a first interface resource object on the target interface based on the first identification information, and then forwards the first data packet using the first interface resource object.

[0137] In another example, an IPv6 packet is used, and the first identification information reuses the flow label field. All or part of the flow label field may be used to indicate the first identification information. For example, referring to FIG. 21, a part of the flow label field is used to indicate the first identification information. For example, the most significant bit in the flow label field is used to indicate the flow label information, and the least significant bit is used to indicate the first identification information. In another example, the least significant bit in the flow label field is used to indicate the flow label information, and the most significant bit is used to indicate the first identification information. The position of the first identification information in the flow label field and the number of bits occupied by the first identification information are not particularly limited in this embodiment of this application.

[0138] After the first network device obtains the first data packet, the first network device determines a target interface based on a destination address in a packet header of the first data packet, then obtains first identification information from a flow label field of the packet header, determines a first interface resource object on the target interface based on the first identification information, and then forwards the first data packet using the first interface resource object.

[0139] In the following, an example is used in which the SDGP-ID corresponds to multiple interface resource objects. The SDGP-ID is combined with the Differentiated Services for QoS (DiffServ) model to indicate the forwarding policy of a particular service flow. Different forwarding policies indicate one or more interface resource objects on the interface of a network device and indicate the forwarding behavior of the interface resource objects.

[0140] When creating a network slice based on the network slice requirement information, the controller configures an SDGP-ID for the network slice and configures an interface resource object for the network slice. The controller configures the SDGP-ID to correspond to multiple interface resource objects. Different SDGP-IDs may correspond to the same interface resource object. The interface resource object corresponding to the SDGP-ID is associated with a PHB used to forward the service flow. It should be noted that the PHBs associated with the same interface resource object corresponding to different SDGP-IDs may be different. That is, one interface resource object belonging to a different network slice may correspond to different PHBs in different network slices. Different PHBs correspond to different forwarding behaviors, and different forwarding behaviors provide different service levels. SDGP-ID 1 is used as an example. SDGP-ID 1 corresponds to N interface resource objects on the target interface, where N is an integer greater than 1. In the entire network, the interface resource object may be identified using a resource ID (Resource-ID, Res-ID). When sending information about the network slice to the target network device, the controller sends to the target network device the mapping relationship between the SDGP-ID and the N interface resource objects, and the mapping relationship between the resource ID and the interface resource object on the target network device. The interface resource objects configured by the controller for each SDGP-ID and the PHB used by each interface resource object corresponding to the SDGP-ID may be considered as a forwarding policy and distributed to each target network device. In one example, the mapping relationship between the SDGP-ID and the N interface resource objects, and the mapping relationship between the resource ID and the interface resource object on the target network device may be used to transmit the information about the network slice to the target network device. It can be understood that different SDGP-IDs correspond to different network slices, and therefore the controller can transmit the correspondence between the SDGP-ID and the identifier of the network slice to the target network device, and the target network device floods the correspondence throughout the network. Alternatively, the controller distributes the correspondence between the SDGP-ID and the identifier of the network slice to each network device in the network topology corresponding to the network slice.

[0141] As an example, three network slices are used: SDGP-ID 1 corresponds to network slice 1, SDGP-ID 2 corresponds to network slice 2, and SDGP-ID 3 corresponds to network slice 3.

[0142] Network slice 1 is a high-priority network slice, which provides a transport service with low packet loss rate, low latency, low jitter, and a determined bandwidth. For network slice 1, the average bandwidth is 25G and the peak bandwidth is 50G. To guarantee the service quality of the slice, the slice allocates resources based on the peak traffic, and the bandwidth of the slice is set to 50G.

[0143] Network slice 2 is a low-priority network slice that provides services with relatively low latency, low packet loss rate, and high reliability. For network slice 2, the average bandwidth is 10 G and the peak bandwidth is 20 G. The slice allocates resources based on the average traffic, and the bandwidth of the slice is set to 10 G.

[0144] Network slice 3 is a low-priority network slice that provides services with relatively low latency, low packet loss rate, and high reliability. For network slice 3, the average bandwidth is 5G and the peak bandwidth is 10G. The slice allocates resources based on the average traffic, and the bandwidth of the slice is set to 5G.

[0145] For example, the interface resource object is a subinterface. Referring to FIG. 22, there are three subinterfaces on each of the first network device and the second network device. The three subinterfaces on the first network device are subinterface 1, subinterface 2, and subinterface 3, respectively. The three subinterfaces on the second network device are subinterface 4, subinterface 5, and subinterface 6, respectively. As shown in the connection relationship of FIG. 22, the three subinterfaces on the first network device are respectively connected to the three subinterfaces on the second network device. Subinterface 1 is connected to subinterface 4 and is provided with a 50 G bandwidth. Subinterface 2 is connected to subinterface 5 and is provided with a 10 G bandwidth. Subinterface 3 is connected to subinterface 6 and is provided with a 5 G bandwidth. The bandwidth corresponding to each subinterface may be planned during network configuration, or the bandwidth of each subinterface may be planned by the controller during network topology planning.

[0146] Different forwarding policies are provided for different network slices based on the requirements of the network slice and the bandwidth of the sub-interfaces on the network device.

[0147] For example, network slice 1 allocates bandwidth resources based on peak traffic to ensure reliable service for high priority services. Network slice 1 may use sub-interface 1 of the first network device and sub-interface 4 of the second network device as forwarding resources and may use EF forwarding behavior. Network slice 2 allocates bandwidth resources based on average traffic to provide reliable service for most service flows. Network slice 2 may use sub-interface 2 of the first network device and sub-interface 5 of the second network device as forwarding resources. If the traffic of a service flow exceeds the average interface bandwidth, the traffic portion exceeding the traffic of the average interface bandwidth may be forwarded using sub-interface 1 and sub-interface 4, or may be forwarded by lowering the service level, for example, forwarded in the AF manner. Network slice 3 allocates bandwidth resources based on average traffic to provide reliable service for most service flows. If the traffic of a service flow exceeds the average traffic, the traffic portion exceeding the average traffic may be forwarded by using sub-interface 2 and sub-interface 5, or may be forwarded by lowering the service level, for example, forwarded in the BE manner.

[0148] Based on this, a forwarding policy can be configured such that a forwarding policy is configured for each different SDGP-ID. The forwarding policy includes the sub-interfaces corresponding to each SDGP-ID and the PHBs used by the sub-interfaces corresponding to the SDGP-ID. For example, -ID The corresponding forwarding policy is SDGP-ID 1: sub-interface 1 of the first network device and sub-interface 4 of the second network device, QoS: EF; SDGP-ID 2: (sub-interface 2 of the first network device and sub-interface 5 of the second network device, QoS: EF) + (sub-interface 1 of the first network device and sub-interface 4 of the second network device + QoS: AF); and SDGP-ID 3: (sub-interface 3 of the first network device and sub-interface 6 of the second network device + QoS: EF) + (sub-interface 2 of the first network device and sub-interface 5 of the second network device + QoS: BE). may be also possible.

[0149] When a subinterface is identified using a resource ID, subinterfaces with the same attribute on different network devices use the same resource ID. That is, when there is one forwarding path between two network devices, the resource ID is used to identify a subpath in the forwarding path between the network devices. For example, referring to FIG. 22, resource ID 1 identifies the subpath between subinterface 1 and subinterface 4, resource ID 2 identifies the subpath between subinterface 2 and subinterface 5, and resource ID 3 identifies the subpath between subinterface 3 and subinterface 6. In this case, the forwarding policy can be expressed as follows: SDGP-ID 1:Res-ID 1+QoS:EF; SDGP-ID 2:(Res-ID 2+QoS:EF)+(Res-ID 1+QoS:AF); and SDGP-ID 3:(Res-ID 3+QoS:EF)+(Res-ID 2+QoS:BE).

[0150] The target network device receives the forwarding policy delivered by the controller. That is, the target network device can establish a mapping-forwarding table after receiving the mapping relationship between the SDGP-ID and the N interface resource objects, and the mapping relationship between the resource ID and the interface resource object on the target network device. For example, the interface resource object is a sub-interface. For example, referring to FIG. 22, three sub-interfaces on the first network device form a binding interface, and three sub-interfaces on the second network device form a binding interface. For example, the binding interface is a trunk interface. In the forwarding plane of the first network device, Mapping and Forwarding The table is generated and maintained based on the correspondence between the sub-interfaces, the Trunk interfaces, the SDGP-IDs, and the Res-IDs, as shown in Table 4. In the forwarding plane of the second network device, Mapping and Forwarding The table is generated and maintained based on the correspondence between the sub-interfaces, the Trunk interfaces, the SDGP-IDs, and the Res-IDs, as shown in Table 5.

[0151] [Table 4]

[0152] [Table 5]

[0153] Shown in Table 4 or Table 5 Mapping and ForwardingIt should be understood that the tables are used only as an example. In the forwarding plane of the target network device, multiple tables are generated and maintained based on the correspondence between the sub-interfaces and the Trunk interfaces, SDGP-IDs, and Res-IDs, respectively. For example, the mapping relationship corresponding to Table 4 may alternatively be established in the manner of Tables 6 and 7.

[0154] [Table 6]

[0155] [Table 7]

[0156] In one example, the target network device can add the PHB used by the sub-interface corresponding to the SDGP-ID to the forwarding table through the mapping, or can store the PHB securely in an independent table or another non-table manner, which is not particularly limited in this application. For example, when establishing the mapping and forwarding table shown in Table 1, the first network device can add the PHB used by the sub-interface corresponding to the SDGP-ID to the mapping and forwarding table as shown in Table 8.

[0157] [Table 8]

[0158] Another procedure for forwarding a service flow by a network device is described below with the aid of an example.

[0159] (1) A first network device obtains a first data packet, where the first data packet carries routing information and first identification information.

[0160] (2) The first network device determines a target interface based on the routing information, the target interface being an interface present on the first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device.

[0161] (3) The first network device determines at least one interface resource object on the target interface based on the first identification information.

[0162] (4) The first network device forwards the first data packet to the second network device using the at least one interface resource object.

[0163] In a specific implementation, the routing information and the first identification information are carried in the first data packet as two separate pieces of information. For example, the routing information is a destination address. Specifically, the method for determining a target interface based on a destination address and the method for determining an interface resource object based on the first identification information are described above. Details will not be described here.

[0164] In one example, a packet header of the first data packet includes a destination address and the first identification information.

[0165] In another example, a packet header of the first data packet includes an extended tag length value (TLV), where the extended TLV includes a destination address and the first identification information.

[0166] In yet another example, the first identification information is included in a packet header of the first data packet as an entropy label.

[0167] In another specific implementation, the first identity can reuse a destination address, and a portion of the destination address is used to indicate the first identity.

[0168] In one example, a packet header of the first data packet includes a destination address, the destination address including routing information and the first identification information. For example, the routing information occupies the most significant bits in the destination address and the first identification information occupies the least significant bits in the destination address. In another example, the routing information occupies the least significant bits in the destination address and the first identification information occupies the most significant bits in the destination address.

[0169] In yet another specific implementation, the first identification information reuses a traffic class field, for example, a packet header of the first data packet includes a destination address (routing information) and a traffic class field, and the traffic class field includes the first identification information.

[0170] In yet another specific implementation, the first identification information reuses a flow label field, and a packet header of the first data packet includes a destination address (routing information) and a flow label field, and the flow label includes the first identification information.

[0171] In one example, the target network device can further add the bandwidth corresponding to each sub-interface to the forwarding table through mapping, or indeed can store the bandwidth in an independent table or another non-table manner, which is not particularly limited in this application.

[0172] For a detailed description of the procedure for forwarding a service flow by a network device, please refer to FIG.

[0173] S1801. A first network device obtains a first data packet, where the first data packet carries a destination address and a first identification information. The first data packet is any data packet in a service flow. There is a mapping relationship between the first identification information and N interface resource objects, where N is an integer greater than 1.

[0174] For a specific method of obtaining the first data packet, please refer to the description of the embodiment corresponding to Figure 12, and details will not be described here.

[0175] S1802. The first network device determines a target interface based on a destination address, the target interface being an interface present on the first network device and configured to connect to a second network device, and the second network device being a next-hop network device of the first network device. For the determination method, please refer to the description of the embodiment corresponding to FIG. 12. Details will not be described here.

[0176] S1803. The first network device determines M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped, where M is a positive integer less than or equal to N.

[0177] S1804. The first network device forwards the first data packet by using one of the M interface resource objects.

[0178] When determining M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped, the first network device can determine M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped based on traffic of the service flow to which the first data packet belongs.

[0179] For example, N is 2. To distinguish the two interface resource objects, the two interface resource objects are respectively called a primary interface resource object and a secondary interface resource object. In other words, the first identification information corresponds to a primary interface resource object and a secondary interface resource object. The first network device can determine the M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped in the following manner.

[0180] If the first network device determines that the bandwidth of the primary interface resource object meets the traffic requirements of the service flow to which the first data packet belongs, the first network device determines that the primary interface resource object should be used to forward the service flow to which the first data packet belongs. In this case, the first network device forwards the first data packet using the primary interface resource object. If the first network device determines that the bandwidth of the primary interface resource object does not meet the traffic requirements of the service flow to which the first data packet belongs, the first network device determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs. In this case, the first network device forwards the service flow to which the first data packet belongs in an offload manner, i.e., forwards the service flow to which the first data packet belongs using the primary interface resource object and the secondary interface resource object. Whether the first data packet should be forwarded using the primary interface resource object or the secondary interface resource object may be determined based on the offload status, such that the first network device forwards the first data packet using the primary interface resource object or the secondary interface resource object.

[0181] If the controller configures different PHBs for different interface resource objects corresponding to the first identity, e.g., a second PHB is used when the primary interface resource object corresponding to the first identity is used to forward the service flow, and a third PHB is used when the secondary interface resource object corresponding to the first identity is used to forward the service flow, then when determining that the primary interface resource object should be used to forward the service flow to which the first data packet belongs, the first network device can forward the first data packet to the second network device using the second PHB and the primary interface resource object. The second PHB may be any of EF, AF, BE, and CS.

[0182] If it is determined that the secondary interface resource object and the primary interface resource object should be used to forward the service flow to which the first data packet belongs, the first network device can forward the service flow to which the first data packet belongs separately by using the second PHB and the primary interface resource object and by using the third PHB and the secondary interface resource object. The second PHB may be any one of EF, AF, BE, and CS, or the third PHB may be any one of EF, AF, BE, and CS. The service level of the PHB corresponding to the primary interface resource object is usually higher than the service level of the secondary interface resource object. For example, the second PHB is EF and the third PHB is AF. When the service flow is forwarded in an offload manner, the primary interface resource object uses EF to ensure reliable service for most of the content of the service flow, and other parts of the content are forwarded in an AF manner after the service level is reduced. In another example, the second PHB is EF and the third PHB is BE. When a service flow is forwarded in an offloaded manner, the primary interface resource object uses EF to ensure reliable service for most of the content of the service flow, and other parts of the content are forwarded in a BE manner after the service level is degraded.

[0183] Continuing with the example shown in FIG. 22, the mapping and forwarding table shown in Table 6 and configured by the first network device is used as an example.

[0184] If service flow 1 in network slice 1 carries SDGP-ID value 1, the procedure for processing service flow 1 by the first network device is as follows.

[0185] A1. A first network device receives a data packet 1 carrying the SDGP-ID, and uses the destination address to query its local routing table to obtain the outbound interface / next hop, e.g., Trunk0, where the next hop network device is the second network device.

[0186] A2. The first network device analyzes data packet 1, consults its mapping and forwarding table (Table 6), and determines that SDGP-ID 1 corresponds to Res-ID 1 and PHB with strict expedited forwarding (EF).

[0187] A3. The first network device changes the PHB in the TC field of the data packet 1 to expedited forwarding (EF).

[0188] A4. The first network device is a sub-interface S1 To obtain the RP / 0 / RSP0 / 2485 Routing Information, the Routing Engine queries the mapping and forwarding table (Table 6) based on the outbound interface and Res-ID 1.

[0189] A5. The first network device is an EF and a sub-interface. S1 The data packet 1 with the modified TC field can be forwarded to the next-hop network device, i.e., the second network device, using a forwarding behavior corresponding to the modified TC field.

[0190] Service flow 2 in network slice 2 carries an SDGP-ID value of 2. The processing steps on the network device side are as follows (assuming that the resource of network slice 2 is 10G and the current traffic value is 15G):

[0191] B1. The first network device receives a data packet 2 carrying the SDGP-ID and uses the destination address to query its local routing table to obtain the outbound interface / next hop Eth-Trunk 0, where the next hop network device is the second network device.

[0192] B2. The first network device analyzes data packet 2, consults its mapping and forwarding table (Table 6), and determines that SDGP-ID 2 corresponds to Res-ID 2 and PHB with Expedited Forwarding (EF), and also corresponds to Res-ID 1 and PHB with Expedited Forwarding (AF).

[0193] B3. The first network device changes the PHB in the TC field of the data packet 2 to expedited forwarding (EF).

[0194] B4. The first network device is a sub-interface S2 Based on the outbound interface and Res-ID 2 Mapping and Forwarding Query the table (Table 6).

[0195] B5. The first network device determines the forwarding behavior and sub-interface corresponding to EF. S2 , to forward the data packet 2 with the modified TC field to the next hop network device, i.e., the second network device.

[0196] B6. The first network device identifies that the bandwidth of the current Sub-interface 2 does not meet the requirements of Service Flow 2, changes the TC field of some packets in Service Flow 2 to AF, and S1 To obtain the Mapping and Forwarding Query the table (Table 6).

[0197] B7. The first network device determines whether the TC field of a service flow is EF and a sub-interface. S1 By using a forwarding behavior corresponding to, it is possible to forward some packets that are modified to a next-hop network device, i.e., the second network device.

[0198] From the above explanation, the sub-interface S1 It can be seen that the sub-interface is used to transport service flows in both network slice 1 and network slice 2. S1 provides EF forwarding behavior to network slice 1, and sub-interface 1 provides strict priority queue scheduling for service flows in network slice 1 to ensure bandwidth and latency for the service flows. S1 provides AF forwarding behavior to network slice 2. Sub-interface 1 provides forwarding quality guarantees for traffic that does not exceed the interface resource bandwidth limit, does not discard traffic that exceeds the limit, and continues to forward traffic after the service level is degraded.

[0199] Service flow 3 in network slice 3 carries SDGP-ID value 3. The processing steps on the first network device are as follows (assuming that the resource of slice 3 is 10 G and the current traffic value is 10 G).

[0200] C1. The first network device receives a data packet 3 carrying the SDGP-ID and uses the destination address to query its local routing table to obtain the outbound interface / next hop Eth-Trunk 0, where the next hop network device is the second network device.

[0201] C2. The first network device analyzes data packet 3, consults its mapping and forwarding table (Table 6), and determines that SDGP-ID=3 corresponds to ResID=3 and PHB with Expedited Forwarding (EF), and also corresponds to ResID=2 and PHB with Expedited Forwarding (AF).

[0202] C3. The first network device changes the PHB in the TC field of data packet 3 to expedited forwarding (EF).

[0203] C4. The first network device S3 Based on the outbound interface and ResID=3 to get Mapping and Forwarding Query the table (Table 6).

[0204] C5. The first network device determines a forwarding behavior and a sub-interface corresponding to EF. S3 to forward the data packet 3 with the modified TC field to the next hop network device, i.e. the second network device.

[0205] C6. The first network device identifies that the bandwidth of the current Sub-interface 3 does not meet the requirements of Service Flow 3, changes the TC field of some packets in Service Flow 3 to BE, and reverts to the bandwidth of the Sub-interface 3. S2 To obtain the Mapping and Forwarding Query the table (Table 6).

[0206] C7. The first network device determines whether the TC field of a service flow is a BE and a sub-interface. S2 , some packets that are modified may be forwarded to a next-hop network device, i.e., the second network device, using a forwarding behavior corresponding to the modified packet.

[0207] Sub-Interface S2The sub-interface is used to transport service flows in both network slice 2 and network slice 3. S2 provides EF forwarding behavior to network slice 2, and sub-interface 2 provides strict priority queue scheduling for service flows in network slice 3 to ensure bandwidth and latency for the service flows. S2 is a network slice 2 and sub-interface 2 provides best effort forwarding behavior to service flows in network slice 3. If sub-interface 2 runs under full load for a long time, data packets in network slice 3 may be lost.

[0208] The SDGP-ID is used to identify the forwarding policy of the service flow. Different network slices can share the same forwarding resource. The forwarding resource mainly serves a specific network slice. When the forwarding resource is idle, the forwarding resource is used to provide a forwarding quality guarantee corresponding to the service flow of another network slice while ensuring the forwarding quality of the service flow of the main network slice, thereby fully utilizing the network resource.

[0209] Based on the same processing principle as the method embodiment, an embodiment of this application further provides an apparatus 1900, as shown in FIG. 24. The apparatus 1900 is applied to a network device. The network device may be the network device in the embodiments shown in FIG. 6, FIG. 10-FIG. 12, FIG. 16, FIG. 22 and FIG. 23, and may be specifically configured to perform the operations of the network device in the aforementioned method embodiment. The apparatus 1900 may include a receiving module 1901, a processing module 1902, and a transmitting module 1903. The apparatus 1900 may specifically be a processor, a chip, a chip system, etc. in a network device. The processing module 1902 is configured to control and manage the operation of the apparatus 1900. The receiving module 1901 is configured to receive information or packets. The transmitting module 1903 is configured to transmit information or packets. The processing module 1902 is configured to process the information or packets received by the receiving module 1901.

[0210] For example, the apparatus is applied to a first network device. The processing module 1902 is configured to obtain a first data packet, the first data packet carrying a destination address and first identification information, determine a target interface based on the destination address, the target interface being an interface present on a first network device and configured to connect to a second network device, the second network device being a next hop network device of the first network device, and determine at least one interface resource object on the target interface based on the first identification information.

[0211] For a specific implementation of determining the target interface based on the destination address by the processing module 1902, please refer to the processing process of step S1202 in the embodiment shown in Figure 12, and details will not be described here.

[0212] For a specific implementation of determining at least one interface resource object on the target interface according to the first identification information by the processing module 1902, please refer to the processing process of step S1203 in the embodiment shown in Fig. 12 or the processing process of step S1803 in the embodiment shown in Fig. 23. Details will not be described here.

[0213] The sending module 1903 is configured to forward the first data packet to the second network device using the at least one interface resource object.

[0214] For a specific implementation of the sending module 1903 forwarding the first data packet to the second network device by using at least one interface resource object, please refer to the processing process of step S1204 in the embodiment shown in Fig. 12 or the processing process of step S1804 in the embodiment shown in Fig. 23. Details will not be described here.

[0215] In a particular implementation, the processing module 1902 is specifically configured to determine a target interface identifier corresponding to a destination address based on a routing and forwarding table, the routing and forwarding table including a correspondence between a destination address and a target interface identifier, and the target interface identifier is used to identify the target interface.

[0216] In a specific implementation, there is a one-to-one mapping relationship between the first identification information and the first interface resource object on the target interface; and The processing module 1902 is specifically configured to determine a first interface resource object corresponding to the first identification information based on the mapping relationship.

[0217] In a particular implementation, the first network device stores a first mapping and forwarding table, the first mapping and forwarding table including a correspondence between an identifier of the first interface resource object and each of the target interface identifier and the first identification information; and The processing module 1902 is specifically configured to determine, based on the first mapping and forwarding table, an identifier of a first interface resource object on a target interface that corresponds to the first identification information and is identified by the target interface identifier, and the identifier of the first interface resource object is used to identify the first interface resource object. For a specific aspect of constructing the first mapping and forwarding table, please refer to the description of the embodiment shown in FIG. 6. Details will not be described here.

[0218] In a particular implementation, when a first interface resource object is used to forward a service flow, a first per-hop behavior (PHB) is used; and The processing module 1902 is particularly configured to determine a first interface resource object corresponding to the first identification information based on the mapping relationship, and then forward the first data packet to the second network device using the first PHB and the first interface resource object.

[0219] In a specific implementation, there is a mapping relationship between the first identification information and N interface resource objects, where N is an integer greater than 1; and The processing module 1902 is specifically configured to determine M interface resource objects to be used for forwarding the service flow to which the first data packet belongs from the N interface resource objects to which the first identification information is mapped, where M is a positive integer less than or equal to N.

[0220] In a particular implementation, the PHB used to transport the service flow may be:M for each of the interface resource objects; and The processing module 1902 is specifically configured to, after determining the M interface resource objects to be used to forward the service flow to which the first data packet belongs, forward the service flow to which the first data packet belongs using the M interface resource objects and the PHBs configured for each of the M interface resource objects.

[0221] In a particular implementation, N is 2, the first identification information corresponds to a primary interface resource object and a secondary interface resource object, and The processing module 1902 is specifically configured to: determine that the primary interface resource object should be used to forward the service flow to which the first data packet belongs when it is determined that the bandwidth of the primary interface resource object meets the traffic requirements of the service flow to which the first data packet belongs; or determine that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs when it is determined that the bandwidth of the primary interface resource object does not meet the traffic requirements of the service flow to which the first data packet belongs.

[0222] In a particular implementation, a second PHB is used when the primary interface resource object is used to transport the service flow, and a third PHB is used when the secondary interface resource object is used to transport the service flow; and The processing module 1902 forwards the first data packet to the second network device by using the second PHB and the primary interface resource object when it determines that the primary interface resource object should be used to forward the service flow to which the first data packet belongs, or forwards the first data packet to the second network device by using the second PHB and the primary interface resource object when it determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs. primary Specifically configured to forward the first data packet to the second network device by using the interface resource object, or to forward the first data packet to the second network device by using a third PHB and a secondary interface resource object.

[0223] In a particular implementation, the second PHB is any one of EF, CS, AF, and BE, or the third PHB is any one of EF, CS, AF, and BE.

[0224] In a particular implementation, the apparatus comprises: receiving a first data packet from a previous hop network device of the first network device; or a receiving module 1901, which is specifically configured to receive a first data packet from a terminal device; Further includes.

[0225] In a particular implementation, the first network device is a head-end network device in a forwarding path of the first data packet, and the apparatus comprises: a receiving module 1901 configured to receive a second data packet, the second data packet being associated with a first network slice; Further comprising: The processing module 1902 is further configured to insert the first identification information into the second data packet based on a correspondence between the identifier of the first network slice and the first identification information to obtain the first data packet.

[0226] In a particular implementation, the target interface is a physical interface, and the interface resource object is a physical interface, a logical interface, or a packet queue; or The target interface is the binding interface and the interface resource object is the physical interface.

[0227] In a particular implementation, the target interface is a binding interface, where the binding interface is configured to establish a neighbor relationship between the first network device and the second network device.

[0228] In a particular implementation, a packet header of the first data packet includes the first identification information.

[0229] In a particular implementation, a packet header of the first data packet includes an extended tag length value (TLV), where the extended TLV includes the first identification information.

[0230] In a particular implementation, the first identification information is included in a packet header of the first data packet as an entropy label.

[0231] In a specific implementation, an interface resource object corresponding to the first identification information is used by the first network slice.

[0232] In another implementation scenario, The processing module 1902 is configured to obtain a first data packet, determine a target interface based on routing information, where the first data packet carries routing information and first identification information, the target interface being an interface present on a first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device, and determine at least one interface resource object on the target interface based on the first identification information.

[0233] The sending module 1903 is configured to forward the first data packet to the second network device using the at least one interface resource object.

[0234] In a particular implementation, the routing information is a destination address. The processing module 1902 is particularly configured to obtain the destination address from the first data packet, determine a target interface based on the destination address, and then determine at least one interface resource object on the target interface based on the first identification information in the first data packet.

[0235] In a particular implementation, a packet header of the first data packet includes a destination address and the first identification information.

[0236] In one possible embodiment, a packet header of the first data packet includes an extended tag length value (TLV), the extended TLV including a destination address and the first identification information.

[0237] In a particular implementation, the first identification information is included in a packet header of the first data packet as an entropy label.

[0238] In a particular implementation, a packet header of the first data packet includes a destination address, the destination address including routing information and first identification information. The processing module 1902 is particularly configured to obtain the destination address from the first data packet, determine a target interface based on the destination address, obtain the first identification information from the destination address, and determine at least one interface resource object on the target interface based on the first identification information.

[0239] In a particular implementation, the routing information occupies the most significant bits in the destination address and the first identification information occupies the least significant bits in the destination address, or alternatively, the routing information occupies the least significant bits in the destination address and the first identification information occupies the most significant bits in the destination address.

[0240] In a particular implementation, a packet header of the first data packet includes a destination address and a traffic class field, and the traffic class field includes first identification information. The processing module 1902 is particularly configured to obtain a destination address from the first data packet, determine a target interface based on the destination address, obtain the first identification information from the traffic class field of the first data packet, and determine at least one interface resource object on the target interface based on the first identification information.

[0241] In a particular implementation, a packet header of the first data packet includes a destination address and a flow label, and the flow label includes a first identification information. The processing module 1902 is particularly configured to obtain a destination address from the first data packet, determine a target interface based on the destination address, obtain the first identification information from a flow label field of the first data packet, and determine at least one interface resource object on the target interface based on the first identification information.

[0242] The embodiment of this application further provides a structure of the network device. As shown in FIG. 25, the network device 2000 may include a communication interface 2010 and a processor 2020. 2000 may be a first network device of any one of the aforementioned embodiments, for example a network device of the embodiments shown in Figures 6, 10 to 12, 16, 22 and 23, and may be specifically configured to perform the operations performed by the network devices of the embodiments shown in Figures 6, 10 to 12, 16, 22 and 23.

[0243] Optionally, the network device 2000 may further include a memory 2030. The memory 2030 may be located inside the network device or outside the network device. The processing module 1902 shown in FIG. 24 may be implemented by the processor 2020. The receiving module 1901 and the transmitting module 1903 may be implemented by the communication interface 2010. The specific connection medium between the communication interface, the processor, and the memory is not limited in this embodiment of the application. In this embodiment of the application, the memory 2030, the processor 2020, and the communication interface 2010 are connected using the bus in FIG. 25. The bus is represented using a thick line in FIG. 25. The manner of connection between the other components is only an example for explanation and does not imply any limitation. The bus may be classified into an address bus, a data bus, a control bus, and the like. For simplicity of representation, only one thick line is used to represent the bus in FIG. 25, but this does not mean that there is only one bus or only one type of bus.

[0244] The processor 2020 is configured to transmit and receive packets or messages by using the communication interface 2010, and to implement any method performed by the network device in any one of the aforementioned embodiments. In the implementation process, the method performed by the network device (e.g., the first network device) in the aforementioned method embodiments may be completed by using instructions in the form of integrated logic circuits of hardware or software in the processor 2020. For the sake of brevity, details will not be described here. The program codes used by the processor 2020 to implement the aforementioned methods may be stored in the memory 2030. The memory 2030 is coupled to the processor 2020.

[0245] In another implementation, the processor 2020 is configured to obtain a first data packet, determine a target interface based on routing information, the first data packet carrying routing information and first identification information, the target interface being an interface present on a first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device, determine at least one interface resource object on the target interface based on the first identification information, and forward the first data packet to the second network device by using the at least one interface resource object.

[0246] The embodiment of this application further provides a structure of a network device. As shown in FIG. 26, the network device 2100 may include a main control board and an interface board. A main control board and an interface board are included. The main control board includes a processor and a memory, and the interface board includes a processor, a memory, and an interface card. The processor of the interface board is configured to call program instructions in the memory of the interface board to transmit and receive packets by using the interface card. The processor of the main control board is configured to call program instructions in the memory of the main control board to perform corresponding processing functions on the packets.

[0247] Based on the same inventive concept as the method embodiment, an embodiment of this application further provides an apparatus. Referring to FIG. 27, the apparatus 2200 is applied to a controller. The apparatus 2200 may include a processing module 2201 and a sending module 2202. The apparatus 2200 may specifically be a processor, a chip or a chip system, a function module, etc. in the controller. The processing module 2201 is configured to control and manage the operation of the apparatus 2200. The processing module 2201 is configured to create a network slice, generate information about the network slice, etc. The sending module 2202 is configured to send information about the network slice.

[0248] For example, the processing module 2201 is configured to create a mapping relationship between the identifier of the first network slice and the first identification information and a mapping relationship between at least one interface resource object in the target interface on the first network device and the first identification information when creating the first network slice, and the first network slice can use the at least one interface resource object. For a specific aspect of creating the mapping relationship between the identifier of the first network slice and the first identification information and the mapping relationship between at least one interface resource object in the target interface on the first network device and the first identification information, please refer to the relevant description of the description of the network slice creation process in the aforementioned method. Details will not be described here.

[0249] The sending module 2202 is configured to send a mapping relationship between the identifier of the first network slice and the first identification information and a mapping relationship between the at least one interface resource object and the first identification information to the first network device.

[0250] The target interface is a physical interface, and ,stomach The interface resource object is a physical sub-interface, a logical sub-interface, or a packet queue; alternatively, the target interface is a binding interface and the interface resource object is a physical interface.

[0251] An embodiment of this application further provides a structure of the controller. As shown in FIG. 28, the controller 2300 may include a communication interface 2310 and a processor 2320. The controller 2300 may be the controller in the above-mentioned method embodiment, and is configured to perform the operation of the controller in the above-mentioned method embodiment. Optionally, the controller 2300 may further include a memory 2330. The memory 2330 may be located inside the controller or outside the controller. The processing module 2201 shown in FIG. 27 may be implemented by the processor 2320. The sending module 2202 may be implemented by the communication interface 2310.

[0252] In the embodiments of this application, the processor may be a general-purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in connection with the embodiments of this application may be directly executed by a hardware processor, or may be executed by using a combination of hardware and software modules in the processor.

[0253] The coupling in this embodiment of the application is ,also is an indirect coupling or communication connection between modules, which may be implemented in an electrical, mechanical or other form; ,also is used for information exchange between modules.

[0254] The processor may cooperate with the memory. The memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory, such as a random-access memory (RAM). The memory may be any medium that can carry or store expected program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such a medium.

[0255] Based on the above embodiment, an embodiment of this application further provides a computer storage medium. The storage medium stores a software program, and when the software program is read and executed by one or more processors, the method provided in any one or more of the above embodiments may be implemented. The computer storage medium may include any medium that can store program code, such as a USB flash drive, a removable hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0256] As will be appreciated by those skilled in the art, the embodiments of this application may be provided as a method, a system, or a computer program product. Thus, this application may take the form of a hardware-only embodiment, a software-only embodiment, or an embodiment involving a combination of software and hardware. Furthermore, this application may take the form of a computer program product embodied in one or more computer usable storage mediums (including, but not limited to, disk memory, CD-ROM, optical memory, etc.) that contain computer usable program code.

[0257] This application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of this application. It should be understood that computer program instructions may be used to implement each process and / or each block in the flowcharts and / or block diagrams, and combinations of processes and / or blocks in the flowcharts and / or block diagrams. These computer program instructions may be provided for a processor of a general purpose computer, a special purpose computer, an embedded processor, or any other programmable data processing device to produce a machine, whereby the instructions executed by the processor of the computer or any other programmable data processing device produce an apparatus for implementing a particular function in one or more processes in the flowcharts and / or one or more blocks in the block diagrams.

[0258] These computer program instructions may be stored in a computer readable memory that can instruct a computer or any other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an artefact that includes an instruction apparatus that implements a particular function in one or more processes in the flowcharts and / or one or more blocks in the block diagrams.

[0259] These computer program instructions may be loaded into a computer or other programmable data processing device, which causes a sequence of operations and steps to be executed on the computer or other programmable device, thereby generating a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps to implement a particular function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.

[0260] Obviously, those skilled in the art may make various modifications and variations to the embodiments of this application without departing from the scope of this application. This application is intended to cover these modifications and variations, provided that they fall within the scope of protection defined by the following claims and their equivalent technologies. [Explanation of symbols]

[0261] 1900 equipment 1901 Receiver Module 1902 Processing Module 1903 Transmitting Module 2000 Network Devices 2010 Communication Interface 2020 Processors 2030 Memory 2100 Network Device 2200 equipment 2201 Processing Module 2202 Transmitting Module 2300 Controller 2310 Communication Interface 2320 Processor 2330 Memory

Claims

1. obtaining a first data packet by a first network device, the first data packet carrying a destination address and first identification information; determining, by the first network device, a target interface based on the destination address, the target interface being an interface on the first network device and configured to connect to a second network device, the second network device being a next hop network device of the first network device; determining, by the first network device, at least one interface resource object on the target interface based on the first identification information; forwarding, by the first network device, the first data packet to the second network device by using the at least one interface resource object; A data transmission control method comprising:

2. The step of determining, by the first network device, a target interface based on the destination address includes: determining, by the first network device, a target interface identifier corresponding to the destination address based on a routing and forwarding table, the routing and forwarding table including a correspondence between the destination address and the target interface identifier, the target interface identifier being used to identify the target interface; 2. The method of claim 1, comprising:

3. There is a one-to-one mapping relationship between the first identification information and a first interface resource object on the target interface; The step of determining, by the first network device, at least one interface resource object on the target interface based on the first identification information, further comprising: determining, by the first network device, the first interface resource object corresponding to the first identity based on the mapping relationship; 3. The method of claim 2, comprising:

4. the first network device stores a first mapping and forwarding table; the first mapping and forwarding table includes a correspondence between an identifier of the first interface resource object and each of the target interface identifier and the first identification information; The step of determining, by the first network device, the first interface resource object corresponding to the first identity based on the mapping relationship, further comprises: determining, by the first network device, based on the first mapping and forwarding table, an identifier of the first interface resource object that corresponds to the first identification information and is on the target interface identified by the target interface identifier, the identifier of the first interface resource object being used to identify the first interface resource object; 4. The method of claim 3, comprising:

5. A first per-hop behavior (PHB) is used when the first interface resource object is used to forward a service flow; The step of forwarding, by the first network device, the first data packet to the second network device by using the at least one interface resource object, further comprising:

5. The method of claim 3 or 4, further comprising: after determining the first interface resource object corresponding to the first identification information based on the mapping relationship, forwarding the first data packet to the second network device by using the first PHB and the first interface resource object, by the first network device.

6. There is a mapping relationship between the first identification information and N interface resource objects, where N is an integer greater than 1; The step of determining, by the first network device, at least one interface resource object on the target interface based on the first identification information, further comprises: determining, by the first network device, from the N interface resource objects to which the first identification information is mapped, M interface resource objects to be used for forwarding a service flow to which the first data packet belongs, where M is a positive integer less than or equal to N; The method according to claim 1 or 2, comprising:

7. a PHB used to transport the service flow is configured for each of the N interface resource objects; The step of forwarding, by the first network device, the first data packet to the second network device by using the at least one interface resource object, further comprising: After determining the M interface resource objects to be used for forwarding the service flow to which the first data packet belongs, forwarding, by the first network device, the service flow to which the first data packet belongs by using the PHB and the M interface resource objects configured for each of the M interface resource objects.

7. The method of claim 6, comprising:

8. N is 2, and the first identification information corresponds to a primary interface resource object and a secondary interface resource object; The step of determining, by the first network device, from the N interface resource objects to which the first identification information is mapped, M interface resource objects to be used for forwarding a service flow to which the first data packet belongs, comprises: determining, by the first network device, that the primary interface resource object should be used to forward the service flow to which the first data packet belongs if the bandwidth of the primary interface resource object satisfies the traffic requirements of the service flow to which the first data packet belongs; or determining, by the first network device, that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs, when determining that the bandwidth of the primary interface resource object does not meet the traffic requirements of the service flow to which the first data packet belongs; 7. The method of claim 6, comprising:

9. a second PHB is used when the primary interface resource object is used to transport the service flow, and a third PHB is used when the secondary interface resource object is used to transport the service flow; The step of forwarding, by the first network device, the first data packet to the second network device by using the at least one interface resource object, further comprising: forwarding, by the first network device, the first data packet to the second network device by using the second PHB and the primary interface resource object if it determines that the primary interface resource object should be used to forward the service flow to which the first data packet belongs; or forwarding, by the first network device, the service flow to which the first data packet belongs by using the second PHB and the primary interface resource object, and forwarding, by the first network device, the service flow to which the first data packet belongs by using the third PHB and the secondary interface resource object, when determining that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs; 9. The method of claim 8, comprising:

10. 10. The method of claim 9, wherein the second PHB is any one of Expedited Forwarding (EF), Class Selector (CS), Assured Forwarding (AF), and Best Effort (BE), or the third PHB is any one of EF, CS, AF, and BE.

11. The step of acquiring a first data packet by a first network device includes: receiving, by the first network device, a first data packet from a previous hop network device of the first network device; or receiving, by the first network device, a first data packet from a terminal device; The method according to any one of claims 1 to 10, comprising:

12. The first network device is a head-end network device in a forwarding path of the first data packet, and the step of acquiring the first data packet by the first network device includes: receiving, by the first network device, a second data packet, the second data packet being associated with a first network slice; inserting, by the first network device, the first identification information into the second data packet based on a correspondence between an identifier of the first network slice and the first identification information to obtain the first data packet; The method according to any one of claims 1 to 10, comprising:

13. the target interface is a physical interface and the interface resource object is a physical sub-interface, a logical sub-interface, or a packet queue; or the target interface is a binding interface and the interface resource object is a physical interface; 13. The method according to any one of claims 1 to 12.

14. 14. The method of claim 13, wherein the target interface is a binding interface, the binding interface configured to establish a neighbor relationship between the first network device and the second network device.

15. 15. The method of claim 1, wherein a packet header of the first data packet includes the first identification information.

16. 16. The method of claim 15, wherein the packet header of the first data packet includes an extended tag length value (TLV), the extended TLV including the first identification information.

17. 16. The method of claim 15, wherein the first identification information is included in the packet header of the first data packet as an entropy label.

18. 15. The method of claim 1, wherein a packet header of the first data packet includes the destination address, and the first identification information occupies K bits in the destination address, where K is a positive integer.

19. 20. The method of claim 18, wherein the K bits are K consecutive least significant bits in the destination address, or the K bits are K consecutive most significant bits in the destination address.

20. 15. The method of claim 1, wherein a packet header of the first data packet includes a traffic class field, the traffic class field including the first identification information.

21. 15. The method of claim 1, wherein a packet header of the first data packet includes a flow label, the flow label including the first identification information.

22. 22. The method according to claim 3, wherein different values ​​of the first identification information correspond to different network slices.

23. The method comprises: receiving, by the first network device, a mapping relationship between an identifier of the network slice and the first identification information and a mapping relationship between the at least one interface resource object in the target interface on the first network device and the first identification information, the mapping relationship being sent by a controller; 23. The method of claim 22, further comprising:

24. obtaining, by a first network device, a first data packet, the first data packet carrying routing information and first identification information; determining, by the first network device, a target interface based on the routing information, the target interface being an interface on the first network device and configured to connect to a second network device, the second network device being a next-hop network device of the first network device; determining, by the first network device, at least one interface resource object on the target interface based on the first identification information; forwarding, by the first network device, the first data packet to the second network device by using the at least one interface resource object; A data packet transmission control method comprising:

25. 25. The method of claim 24, wherein a packet header of the first data packet includes a destination address, the destination address including the routing information and the first identification information.

26. 26. The method of claim 25, wherein the routing information occupies the most significant bits in the destination address and the first identification information occupies the least significant bits in the destination address, or the routing information occupies the least significant bits in the destination address and the first identification information occupies the most significant bits in the destination address.

27. 25. The method of claim 24, wherein a packet header of the first data packet includes a destination address and a traffic class field, the traffic class field including the first identification information.

28. 25. The method of claim 24, wherein a packet header of the first data packet includes a destination address and a flow label, the flow label including the first identification information.

29. When creating a first network slice, creating, by a controller, a mapping relationship between an identifier of the first network slice and a first identification information, and a mapping relationship between at least one interface resource object in a target interface on a first network device and the first identification information, wherein the first network slice uses the at least one interface resource object; sending, by the controller, to the first network device, the mapping relationship between the identifier of the first network slice and the first identification information and the mapping relationship between the at least one interface resource object and the first identification information; A data packet transmission control method comprising:

30. the target interface is a physical interface and the interface resource object is a physical sub-interface, a logical sub-interface, or a packet queue; or the target interface is a binding interface and the interface resource object is a physical interface; 30. The method of claim 29.

31. A data transmission control device, the device being applied to a first network device, a processing module configured to receive a first data packet, the first data packet carrying a destination address and first identification information, determine a target interface based on the destination address, the target interface being an interface on the first network device and configured to connect to a second network device, the second network device being a next hop network device of the first network device, and determine at least one interface resource object on the target interface based on the first identification information; a transmitting module configured to forward the first data packet to the second network device by using the at least one interface resource object; A data transmission control device comprising:

32. 32. The apparatus of claim 31, wherein the processing module is specifically configured to determine a target interface identifier corresponding to the destination address based on a routing and forwarding table, the routing and forwarding table including a correspondence between the destination address and the target interface identifier, and the target interface identifier being used to identify the target interface.

33. There is a one-to-one mapping relationship between the first identification information and a first interface resource object on the target interface; The apparatus of claim 32 , wherein the processing module is specifically configured to determine the first interface resource object corresponding to the first identification information based on the mapping relationship.

34. the first network device stores a first mapping and forwarding table, the first mapping and forwarding table including a correspondence between an identifier of the first interface resource object and each of the target interface identifier and the first identification information; the processing module is specifically configured to determine, based on the first mapping and forwarding table, an identifier of the first interface resource object on the target interface identified by the target interface identifier, which corresponds to the first identification information, and the identifier of the first interface resource object is used to identify the first interface resource object; 34. The apparatus of claim 33.

35. A first per-hop behavior (PHB) is used when the first interface resource object is used to forward a service flow; 35. The apparatus of claim 33 or 34, wherein the processing module is specifically configured to, after determining the first interface resource object corresponding to the first identification information based on the mapping relationship, forward the first data packet to the second network device by using the first PHB and the first interface resource object.

36. There is a mapping relationship between the first identification information and N interface resource objects, where N is an integer greater than 1; The apparatus according to claim 31 or 32, wherein the processing module is specifically configured to determine, from the N interface resource objects to which the first identification information is mapped, M interface resource objects to be used for forwarding a service flow to which the first data packet belongs, where M is a positive integer less than or equal to N.

37. a PHB used to transport the service flow is configured for each of the N interface resource objects; 37. The apparatus of claim 36, wherein the processing module is specifically configured to, after determining the M interface resource objects to be used for forwarding the service flow to which the first data packet belongs, forward the service flow to which the first data packet belongs by using the PHB and the M interface resource objects configured for each of the M interface resource objects.

38. N is 2, and the first identification information corresponds to a primary interface resource object and a secondary interface resource object; 37. The apparatus of claim 36, wherein the processing module is specifically configured to: determine that the primary interface resource object should be used to forward the service flow to which the first data packet belongs if it determines that the bandwidth of the primary interface resource object meets the traffic requirements of the service flow to which the first data packet belongs; or determine that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs if it determines that the bandwidth of the primary interface resource object does not meet the traffic requirements of the service flow to which the first data packet belongs.

39. a second PHB is used when the primary interface resource object is used to transport the service flow, and a third PHB is used when the secondary interface resource object is used to transport the service flow; 39. The apparatus of claim 38, wherein the processing module is particularly configured to: if it determines that the primary interface resource object should be used to forward the service flow to which the first data packet belongs, forward the first data packet to the second network device by using the second PHB and the primary interface resource object; or, if it determines that the primary interface resource object and the secondary interface resource object should be used to forward the service flow to which the first data packet belongs, forward the service flow to which the first data packet belongs to the second network device by using the second PHB and the primary interface resource object and forward the service flow to which the first data packet belongs to the second network device by using the third PHB and the secondary interface resource object.

40. The second PHB is any one of Expedited Forwarding (EF), Class Selector (CS), Assured Forwarding (AF), and Best Effort (BE), or 40. The apparatus of claim 39, wherein the third PHB is any one of EF, CS, AF, and BE.

41. The apparatus comprises: receiving a first data packet from a previous hop network device of the first network device; or a receiving module configured to receive a first data packet from a terminal device; 41. The apparatus of any one of claims 31 to 40, further comprising:

42. the first network device is a head-end network device in a forwarding path of the first data packet, and the apparatus further comprises: a receiving module configured to receive a second data packet, the second data packet being associated with a first network slice; The processing module is further configured to insert the first identification information into the second data packet based on a correspondence between an identifier of the first network slice and the first identification information to obtain the first data packet.

41. Apparatus according to any one of claims 31 to 40.

43. the target interface is a physical interface and the interface resource object is a physical sub-interface, a logical sub-interface, or a packet queue; or 43. The apparatus of claim 31, wherein the target interface is a binding interface and the interface resource object is a physical interface.

44. 44. The apparatus of claim 43, wherein the target interface is a binding interface, the binding interface configured to establish a neighbor relationship between the first network device and the second network device.

45. 45. The apparatus of claim 31, wherein a packet header of the first data packet includes the first identification information.

46. 46. ​​The apparatus of claim 45, wherein the packet header of the first data packet includes an extended tag length value (TLV), the extended TLV including the first identification information.

47. 46. ​​The apparatus of claim 45, wherein the first identification information is included in the packet header of the first data packet as an entropy label.

48. 45. The apparatus of claim 31, wherein a packet header of the first data packet includes the destination address, and the first identification information occupies K bits within the destination address, where K is a positive integer.

49. 49. The apparatus of claim 48, wherein the K bits are the K least significant consecutive bits in the destination address.

50. 45. The apparatus of claim 31, wherein a packet header of the first data packet includes a traffic class field, the traffic class field including the first identification information.

51. 45. The apparatus of claim 31, wherein a packet header of the first data packet includes a flow label, the flow label including the first identification information.

52. 52. The apparatus of claim 33, wherein different values ​​of the first identification information correspond to different network slices.

53. The receiving module includes: receiving a mapping relationship between an identifier of the network slice and the first identification information and a mapping relationship between the at least one interface resource object in the target interface on the first network device and the first identification information, the mapping relationship being sent by a controller; 43. The apparatus of claim 42, further configured:

54. A data packet transmission control device, the device being applied to a controller, comprising: a processing module configured to, when creating a first network slice, create a mapping relationship between an identifier of the first network slice and a first identification information and a mapping relationship between at least one interface resource object in a target interface on a first network device and the first identification information, and to cause the first network slice to use the at least one interface resource object; a sending module configured to send the mapping relationship between the identifier of the first network slice and the first identification information and the mapping relationship between the at least one interface resource object and the first identification information to the first network device; A data packet transmission control device comprising:

55. the target interface is a physical interface and the interface resource object is a physical sub-interface, a logical sub-interface, or a packet queue; or 55. The apparatus of claim 54, wherein the target interface is a binding interface and the interface resource object is a physical interface.

56. A communication interface and a processor, the communication interface is configured to receive a communication message; The processor is configured to communicate with the communication interface and to perform a method according to any one of claims 1 to 28 based on the communication message. Network devices.

57. A communication interface and a processor, the communication interface is configured to receive a communication message; The processor is configured to communicate with the communication interface and to perform the method according to claim 29 or 30 based on the communication message. controller.

58. A computer program comprising instructions, which, when said computer program is run on a computer, enable said computer to carry out the method according to any one of claims 1 to 28.

59. 29. A computer readable storage medium comprising instructions which, when executed on a computer, enable the computer to perform the method of any one of claims 1 to 28.

60. A system comprising an apparatus according to any one of claims 31 to 53 and an apparatus according to any one of claims 54 or 55, or comprising a network device according to claim 56 and a controller according to claim 57.

Citation Information

Patent Citations

  • Network slice method and system

    EP3471341A1