Method and device for realizing network slicing
By using the HQoS scheduling model to manage traffic in network slices, the problem of inflexible and high cost in the existing technology of network slice management is solved, and efficient and refined traffic management is achieved.
Patent Information
- Application Number
- CN202411998254.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-04-25
AI Technical Summary
When implementing network slicing, the prior art has problems such as high cost, large granularity of slice channels, serious resource waste and inflexible management.
The received traffic is processed using the hierarchical quality of service (HQoS) scheduling model, and the tree structure nodes of physical ports, queues and slices are managed to achieve bandwidth management and traffic scheduling for each slice.
It realizes refined management of network slicing, reduces hardware costs, avoids resource waste, and improves management flexibility and fineness.
Smart Images
Figure CN119893578A_ABST
Abstract
Description
Technical Field
[0001] This article relates to network communication technology, and in particular to a method and device for implementing network slicing. Background Art
[0002] With the rapid development of 5G communication network technology and the cloud era, different industries, data services and customers have significantly different requirements for network service quality. Network slicing technology is an on-demand networking method that can separate multiple virtual end-to-end networks in a unified infrastructure network. Each slice is logically isolated, and different levels of business data are transmitted on slices of different logical networks to meet the differentiated needs of different business scenarios for network data. Therefore, how to manage network slices is an urgent problem to be solved. Summary of the invention
[0003] The embodiments of the present application provide a method and device for implementing network slicing.
[0004] A method for implementing network slicing, comprising:
[0005] Get the traffic in the preset network;
[0006] Adopt the scheduling model of hierarchical quality of service HQoS to process the received traffic;
[0007] In the HQoS scheduling model, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein:
[0008] When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue;
[0009] When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice;
[0010] When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
[0011] A device for implementing network slicing, comprising:
[0012] An acquisition module, used to acquire traffic in a preset network;
[0013] A processing module, used to process received traffic using an HQoS scheduling model;
[0014] In the HQoS scheduling model, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein:
[0015] When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue;
[0016] When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice;
[0017] When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
[0018] A storage medium stores a computer program, wherein the computer program is configured to execute the method described above when running.
[0019] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described above.
[0020] In the embodiment of the present application, the HQoS scheduling model is used to manage the received traffic. Based on the inherent functions of the HQoS scheduling model, the nodes where the slices are located in the HQoS scheduling model are used to implement the management operations of the network slices, thereby achieving the purpose of fine-grained management of the traffic. There is no need to use dedicated hardware slice resources, and only conventional hardware resources that support QoS are required to implement network slicing, thereby reducing hardware costs.
[0021] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by implementing the present application. Other advantages of the present application can be realized and obtained by the schemes described in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.
[0023] Figure 1 A flowchart of a method for implementing network slicing provided in an embodiment of the present application;
[0024] Figure 2 A schematic diagram of an HQoS scheduling model provided in an embodiment of the present application;
[0025] Figure 3 A schematic diagram of the correspondence between services and service combinations in an XVLAN provided in an embodiment of the present application;
[0026] Figure 4 A schematic diagram of the corresponding relationship between services and service combinations in an MPLS network provided in an embodiment of the present application;
[0027] Figure 5 A schematic diagram of the structure of an apparatus for implementing network slicing provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] The present application describes multiple embodiments, but the description is exemplary rather than restrictive, and it is obvious to those skilled in the art that there may be more embodiments and implementations within the scope of the embodiments described in the present application. Although many possible feature combinations are shown in the drawings and discussed in the specific embodiments, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with any other feature or element in any other embodiment, or may replace any other feature or element in any other embodiment.
[0029] The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in the present application may also be combined with any conventional features or elements to form a unique invention scheme. Any features or elements of any embodiment may also be combined with features or elements from other invention schemes to form another unique invention scheme. Therefore, it should be understood that any feature shown and / or discussed in the present application may be implemented individually or in any appropriate combination. Therefore, except for the limitations made according to the attached claims and their equivalents, the embodiments are not subject to other restrictions. In addition, various modifications and changes may be made within the scope of protection of the attached claims.
[0030] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not rely on the specific order of the steps described herein, the method or process should not be limited to the steps of the specific order described. As will be understood by those of ordinary skill in the art, other sequences of steps are also possible. Therefore, the specific sequence of the steps set forth in the specification should not be interpreted as a limitation to the claims. In addition, the claims for the method and / or process should not be limited to the steps of performing them in the order written, and those skilled in the art can easily understand that these sequences can be changed and still remain within the spirit and scope of the embodiments of the present application.
[0031] Virtualization technology is used to divide the physical network into multiple independent virtual networks, each of which is called a network slice.
[0032] There are two main ways to implement network slicing in related technologies. One is to rely on proprietary hardware, such as dedicated slicing chips that support FlexE, with a slicing granularity of 5G. The other is to slice based on the service form, where the service form can be divided based on the overall resource concentration, or divided according to specific target customers, or divided according to the priority characteristics of the message.
[0033] Both of the above two implementation methods have technical defects, including:
[0034] Relying on proprietary hardware to implement network slicing has the problems of high solution cost and large granularity of slice channels. In addition, there is serious waste of resources for small bandwidth scenarios, and the bandwidth adjustment of slice channels also needs to be implemented based on protocol interaction, which is a complicated process.
[0035] The planning and construction of slice channels based on the specific information of the business has the problems of inflexible division method and low degree of precision; in addition, it is impossible to execute corresponding scheduling strategies between slice channels, and the flexibility and refinement capabilities are insufficient.
[0036] In view of the technical defects of the related art, the embodiments of the present application provide the following solutions, including:
[0037] Figure 1 A flowchart of a method for implementing network slicing provided in an embodiment of the present application. Figure 1 As shown, the method comprises:
[0038] Step 101: Obtain the traffic in the preset network;
[0039] Among them, the preset network is the network that needs to be managed, and the traffic of the preset network is the traffic that needs to execute network slicing.
[0040] Step 102: Using the HQoS (Hierarchical Quality of Service) scheduling model to process the received traffic;
[0041] The HQoS scheduling model is a tree structure with nested parent and child nodes, where the parent node is the traffic aggregation point of multiple child nodes. The classification rules and control parameters configured on the child nodes will classify and manage the traffic once, and the classification rules and control parameters configured on the parent node will classify and manage the aggregated traffic again.
[0042] In related technologies, the HQoS scheduling model provides refined QoS services for multiple users and multiple services through multi-level queue scheduling. The queues are aggregated in a tree structure, with the flow queue as the leaf node and the subscriber queue as the root node. When a message is hierarchically scheduled, it first enters the leaf node, and after scheduling, it is sent out from the root node.
[0043] Different from the nodes of the HQos scheduling model in the related art, in the embodiment of the present application, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein:
[0044] The physical port is the egress port of the traffic and is configured to perform network slicing operations;
[0045] Queues are used to cache traffic in a preset network, where the data cached in the same queue is data from the same service, where each service can have at least two queues. For example, each service has 8 queues, which can be marked by queues 1-8.
[0046] Slices refer to logical network entities virtualized from the physical network based on specific business needs and service quality requirements. These instantiated slices can run independently of other slices and provide customized network services for specific services or application scenarios.
[0047] In the embodiment of the present application, when the HQoS scheduling model is used to perform hierarchical scheduling on traffic, it first enters the leaf node, and after scheduling, it is sent out from the root node.
[0048] When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue;
[0049] When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice;
[0050] When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
[0051] The method provided in the embodiment of the present application utilizes the HQoS scheduling model to manage the received traffic. Based on the inherent functions of the HQoS scheduling model, the nodes where the slices are located in the HQoS scheduling model are utilized to implement the management operations of network slices, thereby achieving the purpose of refined management of traffic. There is no need to use dedicated hardware slice resources, and only conventional hardware resources that support QoS are required to implement network slicing, thereby reducing hardware costs.
[0052] The method provided in the embodiment of the present application is described below:
[0053] Figure 2 Schematic diagram of the HQoS scheduling model provided in the embodiment of the present application. Figure 2 As shown, in the 5-layer tree structure of the HQoS scheduling model, the root node is the top layer, the leaf node is the bottom layer, and the layers are associated with each other.
[0054] The scheduling model of HQoS is, from top to bottom, a physical interface layer (root node), a network slice layer (slice-group node), a service combination layer (combine-group node), a user service layer (user-group node), and a basic queue layer (leaf node); in addition to physical ports, slices, and queues, the nodes in the scheduling model of HQoS also include services and service combinations as branch nodes, wherein the service combination includes one or at least two services. Therefore, the nodes from bottom to top in the scheduling model of HQoS are queues, services, service combinations, slices, and physical ports.
[0055] exist Figure 2 In the structure shown, for each layer of nodes, the QoS bandwidth of the node is set, and the scheduling information of the child node is set based on the parent node, and it is necessary to verify that the sum of the bandwidth values of its child nodes cannot exceed the bandwidth value of the parent node. The bandwidth value can be specifically the guaranteed bandwidth (Committed Information Rate, CIR) and the peak bandwidth (Peak Information Rate, PIR). Among them, CIR refers to the minimum bandwidth promised for a specific network slice, ensuring that the slice can obtain the agreed bandwidth resources even in the case of network congestion. This is part of a service level agreement (SLA) to ensure the continuity and performance of key services. PIR refers to the maximum bandwidth that a slice can achieve when network conditions permit. It defines the highest peak rate that a slice can use when the network load is light, and is used to temporarily handle sudden traffic demands.
[0056] In addition, you can set the following settings for nodes in the HQoS scheduling model:
[0057] Service priority (PRI): The priority level assigned to different services or traffic flows when network resources are limited. High-priority services will take precedence over low-priority services when network resources are allocated to ensure the performance and service quality of key services.
[0058] Service weight (WEIGHT): A parameter used to describe the importance of different services in resource allocation. Services with high weights will receive more resources during resource allocation, while services with low weights may receive fewer resources.
[0059] Slice Priority (S-PRI): The priority assigned to different network slices during network resource allocation and management. This priority determines which slices can get priority resources when resources are limited. For example, in a 5G network, a network slice used for emergency communications may be given a higher priority to ensure that necessary network resources can be obtained at critical moments.
[0060] Slice weight (S-WEIGHT): An indicator to measure the importance of a network slice, which is usually related to the service capacity of the slice. A slice with a large weight value means that it can provide better services to users, so it will be given priority in resource scheduling. Slice weight can be determined based on different business needs and business benefits. It is a dynamically changing value that can be adjusted according to network conditions and business needs.
[0061] Congestion Scheduling within a Slice (SCHED): When resource competition or congestion occurs within a single network slice, it optimizes network performance by scheduling and managing data within the slice. Specific methods may include technologies such as data packet prioritization, traffic shaping, and queue management to ensure that high-priority data flows are given priority.
[0062] S-SCHED: When there is resource competition or congestion in the entire network, it coordinates the resource allocation between different slices. The specific method involves the resource scheduling strategy across slices, and needs to consider factors such as slice priority, service quality requirements, and business type to ensure the resource utilization efficiency and user experience of the entire network.
[0063] Use the above configuration parameters to configure the nodes of each layer, including:
[0064] In the basic queue layer, set the CIR and PIR of each queue;
[0065] In the user service layer, the CIR and PIR of each service are set to implement the overall rate limit for all queues of each service; in addition, the calling mode and scheduling weight value of each corresponding queue can also be set.
[0066] In the service combination layer, the CIR and PIR of each service combination are set to achieve overall speed limit for all services of each service combination; in addition, the service priority and service weight of each corresponding service can also be set.
[0067] In the network slicing layer, the CIR and PIR of each slice are set to achieve overall speed limit for all service combinations corresponding to each slice; in addition, the congestion scheduling method within the slice can also be set for each slice.
[0068] At the physical interface layer, set the CIR and PIR of each slice to implement the total rate limit for all slices corresponding to each slice; in addition, you can also set the slice priority and slice weight for each slice and configure the congestion scheduling method between slices.
[0069] For example, the CIR of a 10G physical port is 1G, and the PIR is 1.5G. The physical port corresponds to 5 slices, where the maximum bandwidth allowed by each slice is 1.5G. The slice weight ratio of the 5 slices is 1:2:3:4:5, so the maximum value of the traffic allowed to go out of the 5 slices is 0.1G, 0.2G, 0.3G, 0.4G and 0.5G.
[0070] After completing the above configuration, use the HQoS scheduling model to process the received traffic, including:
[0071] When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue;
[0072] When traffic passes through the node where the service is located in the HQoS scheduling model, the traffic in each queue is managed according to the calling mode of the queue and the scheduling weight value under the constraint of the bandwidth value allowed for each service;
[0073] When traffic passes through the node where the service combination in the HQoS scheduling model is located, the traffic of each service is managed according to the service priority and service weight value of the service under the constraint of the bandwidth value allowed to be used by each service combination;
[0074] When traffic passes through the node where the slice is located in the HQoS scheduling model, traffic of each slice is managed according to the congestion scheduling mode within the slice of each slice;
[0075] When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed according to the slice priority and slice weight value based on the congestion scheduling method between slices.
[0076] The bandwidth value allowed to be used by each node in the HQoS scheduling model is set according to slices with a granularity of megabytes (M) to improve the precision of slice management.
[0077] The physical port may be virtualized into N flex-channels, each of which has a corresponding slice, where N is an integer greater than or equal to 2.
[0078] Slice channels are logical channels divided from physical network resources (such as bandwidth and computing resources) for specific network slices. These channels are reserved for specific services or application scenarios to ensure that they can meet specific quality of service (QoS), security level and performance requirements to achieve refined traffic management and resource allocation for different services or users.
[0079] At the physical port of the preset network, N slice channels correspond to N slices one by one, namely slice 1, slice 2, ..., slice N, wherein the characteristic information of the N slices is saved in the slice template.
[0080] exist Figure 2 In the schematic diagram shown, the characteristic information of the slice can be determined based on the nodes under the node where the slice is located and the nodes connected to the node, including: guaranteed bandwidth (CIR), peak bandwidth (PIR), service priority (PRI), service weight (WEIGHT), slice priority (S-PRI), slice weight (S-WEIGHT), congestion scheduling method within the slice (SCHED) and congestion scheduling method between slices (S-SCHED).
[0081] In the slice template, each slice is marked by a unique identifier (SERVICE-ID), wherein the SERVICE-IDs of N slices are SERVICE-1, SERVICE-2, ..., SERVICE-N.
[0082] In related technologies, the division of services in network slicing is based on service type, that is, the specific services that generate traffic, such as signaling, voice, video, or big data transmission.
[0083] In the process of implementing this application, it was found that the relevant technology has the following problems:
[0084] Due to the different network types of the preset network, the basis used for forwarding traffic is different. For example, when forwarding traffic of the same service type, in VLAN, the MAC address needs to be considered when forwarding traffic; in XVLAN (Virtual eXtensibleLocal Area Network), not only the MAC address but also the VLAN network identifier needs to be considered when forwarding traffic; in a three-layer network, IP data packets need to be forwarded based on the five-tuple information.
[0085] In the operation of implementing network slicing, if the division is carried out according to the service types specified in the communication protocol, it is impossible to reflect information such as the network structure and routing characteristics of the preset network, thereby failing to accurately describe the characteristic information of the traffic and achieving refined management of the traffic.
[0086] To solve the above technical problems, the present application proposes the following solutions, including:
[0087] In the embodiment of the present application, the service is determined according to the routing forwarding mode in the preset network, so as to be more in line with the traffic characteristics of the preset network and provide support for more refined management of the traffic of the preset network.
[0088] The routing forwarding method includes keywords used to determine the routing information of the traffic, such as MAC address, VLAN ID, five-tuple (source IP address, destination IP address, protocol number, source port, destination port) information, etc.
[0089] Specifically, when the preset network forwards traffic via IP data packets, the services are divided according to quintuple information of the IP data packets;
[0090] When the preset network forwards traffic via the destination MAC, the services are divided according to the MAC address;
[0091] When the preset network forwards traffic through a VLAN network identifier and a MAC address, the services are divided according to the VLAN network identifier and the MAC address; for example, the preset network is an XVLAN;
[0092] When the preset network forwards traffic through label information, the service is divided according to the pseudowire PW; wherein the label information may be label information of an MPLS network or label information of an SR (Segment Routing) tunnel.
[0093] The following is a description of the method for determining services and service combinations in the embodiments of the present application using a specific application example:
[0094] Figure 3 Schematic diagram of the correspondence between services and service combinations in XVLAN provided in the embodiment of the present application. Figure 3As shown, with the VLAN network identifier as a feature, multiple VLANs can be used as a service individually or in multiples, resulting in P services, namely service 1, service 2, ..., service P, where P is an integer greater than or equal to 2. P services are combined to obtain M service combinations, namely service combination 1, service combination 2, ..., service combination M, where M is an integer greater than or equal to 2, and the service combination has the following characteristics: the same service can only be in the same service combination, where, when P is greater than M, at least two services form a service combination; when P is equal to M, there is a one-to-one mapping relationship between services and service groups. Where, Figure 3 The illustrated method is also applicable to scenarios based on CVLAN (Customer VLAN, user VLAN), SVLAN (Service Provider VLAN, service provider VLAN) or CVLAN+SVLAN forwarding.
[0095] Figure 4 A schematic diagram of the corresponding relationship between services and service combinations in an MPLS network provided in an embodiment of the present application. Figure 4 As shown, with PW as a feature, each PW is used as a service, and P services are obtained, which are PW-1, PW-2, ..., PW-P, where P is an integer greater than or equal to 2; the services using the same LSP are combined to obtain M service combinations, which are LSP-1, LSP-2, ..., LSP-M, where M is an integer greater than or equal to 2. Among them, Figure 4 The method shown is also applicable to label forwarding scenarios where SR tunnels are deployed.
[0096] In an embodiment of the present application, after determining the correspondence between the service and the service combination, the mapping relationship between the slices can be set.
[0097] Specifically, in the ACL (Access Control List), create processing rules for P services to associate the P services with one slice respectively.
[0098] Taking the mapping of service 1 with VLAN network identifier 100 to slice 1 (identified as SERVICE-1) as an example, an entry is created, in which the matching condition of the entry is that the VLAN network identifier is 100 and the associated action is SERVICE-1, so as to achieve the purpose of flexible diversion.
[0099] From the above example, we can see that the difference between the traffic diversion operations of each service in the ACL is only the content of the entry. Therefore, when the slice matched by the service changes, you only need to update the associated action in the entry of the service and modify the associated action to the updated SERVICE-ID.
[0100] Utilize the ACL table to create soft-mapped relationships, which can be modified flexibly and dynamically, thus reducing maintenance costs.
[0101] After determining the correspondence between services and service combinations and the mapping relationship between services and slices, the mapping relationship between services, service combinations, and slices can be determined. In the HQoS scheduling model, the ratio of the number of nodes from bottom to top is P:M:N, where P≥M≥N.
[0102] In addition, when determining the mapping relationship, the bandwidth configuration data of each service, each service combination, and each slice can also be determined based on the CIR and PIR of the physical port.
[0103] In the above implementation, the physical port is a slice port of a chip supporting FlexE;
[0104] Among them, after the chip supporting FlexE completes the network slicing operation, the HQoS scheduling model is used to process the traffic in the slice output by the FlexE chip.
[0105] Since the minimum slot allocation unit of FlexE configuration is 5G, the granularity is relatively large. After the chip supporting FlexE completes the network slicing operation, the HQoS scheduling model is used to perform secondary slicing on the slice port created based on FlexE to meet the low-speed scenario and can flexibly respond to various scenarios. In addition, after the FlexE slice port is created, it is represented as a physical port with real MAC attributes in the hardware, which can be used directly, and the usage method is no different from that of an ordinary port.
[0106] In actual applications, based on the scale of the network and traffic characteristics (such as bandwidth parameters, service type, priority, etc.), the number of slice channels in the physical port is determined; the mapping relationship between services, service combinations and slices is determined; then, based on the obtained mapping information, the HQoS scheduling model is constructed, and the configuration parameters of each node in the scheduling model are set to complete the deployment operation of the HoS scheduling model.
[0107] The method provided in the embodiment of the present application realizes refined slice bandwidth control, and can specifically control the bandwidth granularity of the slice to reach the M level, so as to provide bandwidth services to customers more accurately. The intra-slice congestion scheduling method and the inter-slice congestion scheduling method can flexibly adjust the bandwidth of the slice. In addition, only conventional hardware resources that support QoS are needed to achieve the purpose of network slicing, which is low-cost and compatible with networks that support hard slicing.
[0108] Figure 5 A schematic diagram of the structure of a device for implementing network slicing provided in an embodiment of the present application. Figure 5As shown, the device comprises:
[0109] The acquisition module 501 is used to acquire the traffic in the preset network;
[0110] The processing module 502 is used to process the received traffic using the HQoS scheduling model;
[0111] In the HQoS scheduling model, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein:
[0112] When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue;
[0113] When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice;
[0114] When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
[0115] The above device is deployed in a chip that supports FlexE.
[0116] The device provided in the embodiment of the present application uses the HQoS scheduling model to manage the received traffic. Based on the inherent functions of the HQoS scheduling model, the node where the slice is located in the HQoS scheduling model is used to implement the management operation of the network slice, thereby achieving the purpose of refined management of the traffic. There is no need to use dedicated hardware slice resources, and only conventional hardware resources that support QoS are required to implement network slicing, thereby reducing hardware costs.
[0117] An embodiment of the present application provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the method described above when running.
[0118] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described above.
[0119] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.
Claims
1. A method for implementing network slicing, characterized in that: include: Get the traffic in the preset network; Adopt the scheduling model of hierarchical quality of service HQoS to process the received traffic; In the HQoS scheduling model, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein: When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue; When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice; When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
2. The method according to claim 1, characterized in that: When traffic passes through the node where the slice is located in the HQoS scheduling model, traffic of each slice is managed according to the congestion scheduling mode within the slice of each slice; When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed according to the slice priority and slice weight value based on the congestion scheduling method between slices.
3. The method according to claim 1, characterized in that: The HQoS scheduling model also includes services and service combinations as branch nodes, wherein the service combination includes one or at least two services; wherein: When traffic passes through the node where the service is located in the HQoS scheduling model, the traffic in each queue is managed according to the calling mode of the queue and the scheduling weight value under the constraint of the bandwidth value allowed for each service; When traffic passes through the node where the service combination is located in the HQoS scheduling model, the traffic of each service is managed according to the service priority and service weight value of the service under the constraint of the bandwidth value allowed to be used by each service combination.
4. The method according to claim 3, characterized in that The service is determined according to the routing forwarding mode in the preset network.
5. The method according to claim 4, The invention is characterized in that: When the preset network forwards traffic via IP data packets, the services are divided according to the five-tuple information of the IP data packets; When the preset network forwards traffic via the destination MAC, the services are divided according to the MAC address; When the preset network forwards traffic via the VLAN network identifier and the MAC address, the services are divided according to the VLAN network identifier and the MAC address; When the preset network forwards traffic through label information, the services are divided according to pseudo wires PW.
6. The method according to claim 3, characterized in that: The bandwidth value allowed to be used by each node in the HQoS scheduling model is set based on slices with a granularity of megabytes.
7. The method according to any one of claims 1 to 6, characterized in that: The physical port is a slice port of a chip supporting FlexE; Among them, after the chip supporting FlexE completes the network slicing operation, the HQoS scheduling model is used to process the traffic in the slice output by the FlexE chip.
8. A device for implementing network slicing, characterized in that: include: An acquisition module, used to acquire traffic in a preset network; A processing module, used to process the received traffic using the HQoS scheduling model; In the HQoS scheduling model, the physical port is the root node, the queue is the leaf node, and the slice is the child node of the root node; wherein: When traffic passes through the node where the queue in the HQoS scheduling model is located, traffic to be sent is cached in the queue under the constraint of the bandwidth value allowed to be used by each queue; When traffic passes through the node where the slice is located in the HQoS scheduling model, the traffic of each slice is managed under the constraint of the bandwidth value allowed to be used by each slice; When traffic passes through the node where the physical port is located in the HQoS scheduling model, traffic of all slices is managed under the constraint of the bandwidth value allowed to be used by the physical port.
9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 7.