CN117499352A

CN117499352A - Active identification and forwarding method and system for TSN (traffic channel network) mixed traffic

Info

Publication number: CN117499352A
Application number: CN202311215249.XA
Authority: CN
Inventors: 李龙飞; 陈卫国; 马徐瀚; 董劭颖; 王凯乐; 冯海强; 周钰全; 王剑峰; 李海松; 杨靓
Original assignee: Xian Microelectronics Technology Institute
Current assignee: Xian Microelectronics Technology Institute
Priority date: 2023-09-19
Filing date: 2023-09-19
Publication date: 2024-02-02

Abstract

The invention discloses an active identification and forwarding method and system for TSN mixed flow, which belong to the field of integrated circuits, wherein a data flow is rapidly and actively identified and perceived in a controller sending path, an outpRVLAN is adopted as TSN_tag to actively identify a full service flow, and key information in an ST flow is extracted to form a specific descriptor for characterization; on the basis, the forwarding table is quickly inquired and updated through the descriptor, a special tunnel is established for the ST flow on the control plane of the exchanger, and efficient and accurate forwarding is completed, so that the residence time of the ST flow in the exchange is reduced, and the certainty of data transmission is improved; and finally, stripping the TSN_Tag in the data frame at the terminal controller, and keeping transparent to the upper layer application.

Description

Active identification and forwarding method and system for TSN (traffic channel network) mixed traffic

Technical Field

The invention belongs to the technical field of integrated circuits, and particularly relates to an active identification and quick forwarding method for time-sensitive network (Time Sensitive Network, TSN) hybrid traffic.

Background

Currently, it is generally desirable to achieve high quality bearers for various traffic flows in time sensitive networks, mainly including BE (Best Effort) "best effort" data flows, RC (Rate Constraint) "rate limited" data flows, and ST (Scheduled Traffic) "time determined" data flows. When there is a mixed traffic transmission of BE, RC and ST in the network, it is necessary to BE able to identify these traffic and to process them by adopting different scheduling algorithms to ensure the quality of service.

In the presently disclosed time sensitive network solutions, classification and identification of data flows in TSN switches is commonly employed, or before performing a data scheduling algorithm, to achieve different quality of service treatments for different flows. In general, the data stream is identified in a "five-tuple" manner in the ethernet data frame, that is, a data stream is determined by a vector formed by a source IP address, a destination IP address, a source port, a destination port, and a type, and then a data stream of which type is determined by HASH calculation and table lookup. Different vendors may use different characteristics in the data frame to determine the data flow. For example, in the product of Xinhua three H3C, it matches critical traffic messages by source MAC address, destination MAC address, coS value, and VLAN ID. Wherein, the more parameters specified, the more accurate the matching result. After the data flow enters the TSN switch, the device maps the TSN flow and the non-TSN flow into queues of different interfaces according to the flow characteristics, and then different scheduling processing modes are adopted.

In summary, whatever characteristics are adopted to judge the data stream, the key idea is to extract key information in the data frame and perform operations such as calculation, table lookup and the like so as to determine the type of the data stream. In this way, the devices such as the controller and the switch in the TSN network can continuously identify the current transmitted data stream, and different processing modes are adopted according to different types of streams, stream IDs and the like, so as to achieve the effect of differentiating the service quality.

The method is simple and easy to realize, and can ensure that the data streams bearing different services are identified and processed by hardware by carrying out advanced deployment and planning on each device in the TSN network. However, the above method requires that each device in the network has discrimination capability for the data stream, i.e., each device, whether a switch or a controller, must have a function of classifying and identifying the data stream as long as it is in the data transmission path. In this way, the hardware resource overhead of the network equipment is increased, the network deployment complexity is improved, and the network transmission delay and jitter are increased, so that the deterministic data flow is seriously affected.

In order to improve the classification and recognition efficiency of data streams and reduce the data transmission delay and jitter, much research is focused on how to accelerate the calculation optimization method of data frame feature extraction and matching, such as parallel HASH calculation and query methods, TCAM units, and the like. These methods accelerate the recognition of the data stream through concurrent processing, but generally require a large hardware overhead, resulting in an increase in power consumption and hardware complexity. Furthermore, although the above-described optimization methods can accelerate the recognition of data traffic to some extent, these methods solve the problem only locally and do not solve the problem at the system level. The system layer is to make an omnibearing and full-flow solution according to modes of path selection, sending processing, forwarding processing, receiving processing and the like of data transmission in a network architecture so as to realize autonomous identification and rapid forwarding of data traffic and ensure the certainty of network transmission.

Disclosure of Invention

The invention provides an active identification and forwarding method and system for TSN mixed traffic, which improve traffic identification efficiency and transmission certainty of a TSN time sensitive network when mixed traffic is transmitted.

In order to achieve the above purpose, the present invention adopts the following technical scheme:

an active identification and forwarding method for TSN mixed flow comprises the following steps:

s1, extracting key information in all data frames in a data stream in a first controller, wherein the extracted content forms a corresponding frame information vector; according to the frame information vector, hash calculation is carried out to obtain a Hash index value, the Hash index value is directly used as an address to read the content in the mapping table, and RC flow and ST flow are identified; if the data stream cannot BE identified, the data stream is a BE stream;

s2, forwarding according to the data stream type:

if the data stream is BE stream or RC stream, directly forwarding;

if the data stream is ST stream, inserting TSN_Tag into the data frame in the ST stream, calculating and replacing CRC checksum of the data frame again, and sending the data stream to a data output port of the exchanger; inquiring a forwarding port according to the data stream ID, and selecting a special channel to forward the data stream from a data output port of the switch to the second controller;

the second controller judges whether the received data stream is provided with TSN_Tag or not, and if the received data stream is not provided with TSN_Tag, the second controller receives the data stream; if the TSN_Tag is provided, the TSN_Tag is stripped, and the descriptor is updated and then the data stream is received.

Further, in step S1, the frame information vector includes a source MAC address, a destination MAC address, a source IP address, a destination IP address, a source port, a destination port, and a frame type.

Further, in step S1, the flow type, the flow ID, the queue number and the corresponding frame information vector are recorded in the mapping table, and the table is configured in advance according to the application requirement.

Further, each entry in the mapping table records the original frame information vector, and only when the frame information vector is hit in the query process, the frame information vector is hit, otherwise, the frame information vector is processed according to the missed data frame.

Further, in step S2, tsn_tag insertion is implemented based on double_vlan technology.

Further, in step S2, the position of the outer_vlan is used as tsn_tag.

Further, in step S2, the tsn_tag is composed of 4 bytes, where the first two bytes are flow identification information, and the reserved field that is not used in the ethernet protocol type is used for characterization; the last two bytes are the stream ID, 16 bits total.

Further, in step S2, when the data stream is sent to the data output port of the switch, when the data frame in the data stream is written into the entry buffer module of the switch, the content in the data frame is synchronously extracted and parsed, and if the tsn_tag is parsed, the query of the forwarding table is performed according to the stream ID, so as to obtain the data output port; the TSN_Tag is analyzed in the first clock period of the data frame written-in entry buffer module, inquiry is carried out in the second clock period, and an inquiry result is obtained in the third clock period; the ingress buffer module read operation begins a third clock cycle after the ingress buffer module write.

Further, in step S2, when forwarding the data stream from the data output port of the switch to the second controller, for each determined data output port, a data path between the data output port and all other data output ports is established, and the ST stream performs data transmission between the data output ports through the corresponding data path in a time division multiplexing manner based on the global time.

An active identification and forwarding system for TSN hybrid traffic, comprising:

the TSN controller is used for identifying, marking and de-marking the data stream;

the TSN exchanger is used for realizing the two-layer forwarding of the data stream among the ports, simultaneously completing the quick query of the forwarding table aiming at the ST stream and realizing the forwarding through a special data channel;

the TSN controller includes:

1) The frame analysis unit is used for extracting quintuple information in all data frames in the transmission data stream according to the configuration of the register, forming corresponding frame information vectors by the extracted quintuple information, and outputting the corresponding frame information vectors and the data frames to the stream management unit;

2) The stream management unit is used for identifying BE stream, RC stream and ST stream in the transmitting process, establishing a mapping relation between a data frame and a stream ID, determining a transmitting queue number of the data stream, and storing the data frame and related frame descriptors into corresponding queues;

3) The queue management unit is used for completing TSN queue scheduling according to the data frame enqueuing and register configuration conditions and determining a queue capable of outputting at the current moment;

4) The MAC transmitting unit is used for completing the transmission of the corresponding data frames according to the content of the frame descriptor and inserting TSN_Tag into the data frames in the ST stream in the transmission process;

5) The MAC receiving unit is used for receiving the data stream, finishing stripping of TSN_Tag for the ST stream at the same time, and storing the stripped TSN_Tag as receiving state information of a corresponding frame into a frame descriptor corresponding to the frame;

6) The register unit comprises a control register and a status register, wherein the control register is used for configuring functions, working modes and the like of each module, and the status register is used for recording the working state of each module;

the TSN switch includes:

1) The data frame preprocessing unit is used for identifying and analyzing TSN_Tag in the data frame input by the port, finishing inquiry of a forwarding table according to the analyzed ST stream ID, and determining a data output port;

2) And the forwarding unit is used for directly transmitting the data frame to the data output port according to the forwarding result.

Compared with the prior art, the invention has at least the following beneficial technical effects:

the invention provides an active identification and forwarding method and system for TSN mixed flow, which adopts a systematic idea, firstly, based on double_VLAN technology, quick and active identification and perception are carried out on data flow in a controller sending path, outpRVLAN is adopted as TSN_tag to carry out active identification on all service flow, and meanwhile, key information in ST flow is extracted to form specific descriptors for characterization; on the basis, the forwarding table is quickly inquired and updated through the descriptor, a special tunnel is established for the ST flow on the control plane of the exchanger, and efficient and accurate forwarding is completed, so that the residence time of the ST flow in the exchange is reduced, and the certainty of data transmission is improved; and finally, stripping the TSN_Tag in the data frame at the terminal controller, and keeping transparent to the upper layer application.

The invention establishes a systematic optimization method aiming at the TSN controller and the exchanger, can realize autonomous identification and marking of BE, RC and ST flows according to TSN_Tag when mixed flow communication is carried out in a network, simultaneously realizes quick forwarding processing of ST flows, has higher expandability and flexibility, and can well support the requirements of the TSN network on data transmission certainty, instantaneity and low jitter.

Drawings

FIG. 1 is a process flow diagram of the method of the present invention;

fig. 2 is a schematic diagram of a core unit of a TSN controller according to the present invention; wherein the inside of the dotted line is the core unit structure of the controller related to the invention;

FIG. 3 is a schematic diagram of a core unit of a TSN switch according to the present invention; wherein the inside of the dotted line is the core unit structure of the exchanger related to the invention;

FIG. 4 is a TSN_Tag format defined in the present invention;

FIG. 5 is a diagram of simulation test results of frame information parsed by the method of the present invention;

fig. 6 is a diagram of a simulation test result of a fast forwarding function according to the method of the present invention.

Detailed Description

In order to make the purpose and technical scheme of the invention clearer and easier to understand. The present invention will now be described in further detail with reference to the drawings and examples, which are given for the purpose of illustration only and are not intended to limit the invention thereto.

In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more. In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.

In order to improve the flow identification efficiency and the transmission certainty of the TSN time-sensitive network when mixed flow transmission is carried out, the invention establishes a systematic optimization method aiming at a TSN controller and a exchanger to realize autonomous identification of BE, RC and ST flows, simultaneously realizes quick forwarding processing of ST flows, and further ensures the certainty of TSN network data transmission on the premise of reducing the hardware design complexity of the controller and the exchanger.

Example 1

An active identification and forwarding system for TSN mixed flow comprises the following steps:

s1, extracting quintuple information in all data frames in a data stream in a first controller, wherein the extracted content forms a corresponding frame information vector; according to the frame information vector, hash calculation is carried out to obtain a Hash index value, the Hash index value is directly used as an address to read the content in the mapping table, and BE flow, RC flow and ST flow are identified: if the stream can be found from the mapping table, identifying the stream as an ST stream or an RC stream through the mapping table; otherwise, it is BE flow. The mapping table records the stream type, stream ID, queue number and corresponding frame information vector, and the user needs to configure the table in advance according to the application requirement. It should be noted that only the mapping relationship between RC stream and ST stream is recorded in the mapping table.

S2, forwarding according to the data stream type:

if the data stream is BE stream or RC stream, the first controller directly performs the sending operation;

if the data stream is an ST stream, the first controller inserts TSN_Tag into the data frame in the ST stream, calculates and replaces the CRC checksum of the data frame again, and sends the data stream to the exchange port; the exchanger inquires the forwarding port according to the data stream ID, and selects a special channel to forward the data stream from the data output port of the exchanger to the second controller;

Example 2

The active identification and forwarding system for TSN-oriented mixed traffic described in embodiment 1 is mainly implemented by mutually cooperating a TSN controller and a TSN switch. The controller mainly completes identification, marking and unmarking of the data flow, and the exchanger mainly completes quick query and forwarding based on marking. The functions that the TSN controller and the switch need to perform are described in detail below.

TSN controller

Referring to fig. 2, the controller mainly performs identification, marking and unmarking of the data stream, and is composed of a frame parsing unit, a stream management unit, a queue management unit, a MAC transmitting unit, a MAC receiving unit and a register unit.

1. The main function of the frame analysis unit is to extract five-tuple information in all data frames in the sending data stream according to the configuration of the register, and transmit the extracted information to the stream management unit. The interface through which the frame parsing module is connected to the upstream processor is typically a PCIe, emif, AXI interface or the like, through which the processor passes the data to be sent to the controller.

The frame analysis module supports line speed processing, analyzes and extracts data content input by the processor interface in real time, and the extracted information is determined by the configuration of the register module, wherein the extracted information comprises a source MAC address, a destination MAC address, a source IP address, a destination IP address, a source port, a destination port, a frame type and the like in an Ethernet data frame. The extracted content forms a corresponding frame information vector, and is output to a stream management unit together with the data frame.

2. The main function of the stream management unit is to identify BE stream, RC stream and ST stream in the transmitting process, establish the mapping relation between data frame and stream ID, determine the transmitting queue number of the data stream, and store the data frame and related frame descriptors into corresponding queues.

The stream management unit is mainly composed of a Hash calculation module and a table lookup module. The Hash calculation module adopts a Toeplitz Hash calculation mode, and completes the Hash calculation and obtains a Hash index value according to the frame information vector input by the frame analysis module. The lookup module consists of a query module and a mapping table, wherein the query module directly uses the Hash index value as an address to read the content in the mapping table; if it can BE found from the mapping table, it is indicated that the stream is an ST stream or an RC stream, otherwise, it is an or BE stream. The mapping table records the stream type, stream ID, queue number and corresponding frame information vector, and the user needs to configure the table in advance according to the application requirement. It should be noted that only the mapping relationship between RC and ST streams is recorded in the mapping table.

Based on the content queried in the mapping table, the stream management unit may determine the frame type, stream ID, queue number and associated control information of the data frame. For the missed data frames, the data frames are processed according to BE flow and output to a fixed queue.

To prevent a "false positive" event from occurring, each entry in the mapping table records the original frame information vector, which can BE considered a true hit only if it hits during the query, otherwise it is treated as a missing data frame, i.e. BE stream.

3. The main function of the queue management unit is to complete a TSN queue scheduling algorithm (such as Qbv, CBS, qch, SP) according to the data frame enqueuing and register configuration conditions, and determine a queue capable of outputting at the current moment.

In each queue, the frame descriptor records, in addition to the address and length of the frame stored in the transmission buffer, the stream type, stream ID, and corresponding transmission operation corresponding to the frame, for example, whether to replace the source MAC address during transmission, whether to insert CRC, and the like.

At a certain time, the queue management unit only selects one queue for data transmission, and passes the transmission data frame descriptor to the MAC transmission unit.

4. The main function of the MAC transmitting unit is to complete the transmission of the corresponding data frame according to the content of the frame descriptor, and to insert TSN_tag into the data frame in the ST stream in the transmission process. The MAC transmitting unit implements fast insertion of tsn_tag based on double_vlan technology. The main function of tsn_tag is to allow the switch, controller, to quickly identify the type of data frame (whether ST stream or not) and the corresponding stream ID.

The MAC transmitting unit marks the ST stream and stream ID, the RC stream and stream ID using the location of the outer_vlan as tsn_tag. For BE flows, no processing is performed. Since tsn_tag is inserted at the outer_vlan, this way no effect is exerted on the VLAN of the original frame.

Referring to fig. 4, tsn_tag is composed of 4 bytes in total, wherein the first two bytes are stream identification information, wherein 0x82A1 represents ST stream, characterized by reserved fields that are not used in the ethernet protocol type. The last two bytes are the stream ID, 16 bits total, which can represent 65536 streams.

Due to the insertion of the tsn_tag, the MAC transmitting unit will recalculate and replace the CRC checksum of the data frame at transmission.

5. The main function of the MAC receiving unit is to complete the reception of the data frame while the stripping of tsn_tag is completed for the ST stream. The stripped TSN_Tag is used as the receiving state information of the frame and is stored in the frame descriptor corresponding to the frame so as to be used by the receiving processing flow.

Since the stripping of tsn_tag is implemented in hardware at the MAC layer, the entire process is transparent to the upper layer applications.

6. The register unit mainly comprises a control register and a status register, wherein the control register is used for configuring functions, working modes and the like of each module, and the status register is used for recording working states of each module.

TSN exchanger

Referring to fig. 3, the switch mainly completes two-layer forwarding of various data flows between ports, and simultaneously completes fast query of forwarding tables for ST flows, and realizes forwarding through a dedicated data channel. Based on the traditional Ethernet switching structure, the special processing flow for ST flow is mainly composed of a data frame preprocessing unit and a tunnel forwarding unit.

1. Data frame preprocessing unit

The main functions of the data frame preprocessing unit are as follows: and completing identification and analysis of TSN_Tag in the data frame input by the port, completing inquiry of a forwarding table according to the analyzed ST flow ID, and determining the data output port. Because ST streams have severe requirements on transmission certainty, the data frame preprocessing unit adopts line speed processing in the processing process to reduce the residence time of data inside the switch. The data frame preprocessing unit mainly comprises an entry cache module, an analysis module and a forwarding table query module. The working mode is as follows:

the entry buffer module is composed of a synchronous FIFO for buffering data frames received by the port. And when the data frame is written into the FIFO, the analysis module synchronously extracts and analyzes the content in the data frame, and if the TSN_tag is analyzed, the query of the forwarding table is performed according to the stream ID, so that a data output port is obtained. Since the data width of the FIFO is 128 bits (16 bytes), the tsn_tag is located at 12-16 bytes of the frame header, so that the tsn_tag can be resolved in the first clock cycle of writing the data frame into the FIFO, the inquiry is performed in the second clock cycle, and the inquiry result is obtained in the third clock cycle. The FIFO read operation starts a third clock cycle after FIFO writing to ensure that data is transferred to the "tunnel" forwarding element in synchronization with the data output port control information.

2. "Tunnel" forwarding unit

The main functions of the "tunnel" forwarding unit are: according to the forwarding result, the data frame is directly transmitted to the data output port, which is a data transmitting unit, and the data is forwarded in a tunnel-like manner without the traditional shared buffer mode in the whole forwarding process. "tunnel" forwarding requires a dedicated path to be reserved between the ports to ensure that no collisions occur when forwarding ST streams.

For each determined port, the "tunnel" forwarding unit will establish the data path for that port with all other ports, thus, for a switch with N ports, a total of N x (N-1) data paths need to be established. Because the ST flow adopts a time division multiplexing mode to carry out data transmission among ports based on global time, under reasonable service debugging, only one path in each 'tunnel' forwarding unit is selected at a certain moment, namely the phenomenon that a plurality of 'tunnel' forwarding units forward to the same output port does not occur.

It should BE noted that only ST flows will BE forwarded by the "tunnel" forwarding unit, and conventional shared buffer mode is still used for forwarding RC and BE flows.

The invention can be used in controllers and exchanger chips in TSN networks, can provide autonomous and rapid identification of traffic for transmission of mixed traffic, and can accelerate forwarding efficiency of ST flow in the whole network, thereby improving certainty and instantaneity.

In a specific embodiment, the self-developed gigabit TSN controller LCTSNEP01 and TSN switch LCTSNSW16 are selected as objects, and the method of the invention is implemented in the design and verification at the system level and prototype level is performed. LCTSNEP01 and LCTSNSW16 together form a system solution for a gigabit TSN network capable of providing high quality bearers for full traffic flows for users.

Through simulation verification, the result is shown in fig. 5, and the mapping table is queried by utilizing the parsed frame information through the control of the state machine, the result is compared with the parsed stream ID, the result is matched, and the table lookup content is indicated to be effective.

For the fast forwarding function, the simulation result is shown in fig. 6, and the frame preprocessing unit classifies the streams and receives and processes two types of data frames in parallel. Because of the use of separate memory areas, two data frames can be received simultaneously and written separately into the respective memory areas without affecting each other.

Through FPGA prototype verification, the data transmission single-hop switching delay is less than 10us and the transmission jitter is less than 1us for ST flows. The verification result shows that the invention realizes the expected design function, can autonomously complete the identification and marking of the data flow, can complete the insertion and stripping of TSN_Tag based on hardware in the controller, can realize the rapid forwarding of ST flow in the exchanger, well ensures the service quality of ST flow, and improves the transmission performance of the whole TSN network to the mixed flow.

The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.

Claims

1. The active identification and forwarding method for the TSN hybrid traffic is characterized by comprising the following steps:

s2, forwarding according to the data stream type:

if the data stream is BE stream or RC stream, directly forwarding;

2. The method according to claim 1, wherein in the step S1, the frame information vector includes a source MAC address, a destination MAC address, a source IP address, a destination IP address, a source port, a destination port, and a frame type.

3. The method for actively identifying and forwarding TSN-oriented mixed traffic according to claim 1, wherein in step S1, a flow type, a flow ID, a queue number and a corresponding frame information vector are recorded in the mapping table, and the table is configured in advance according to application requirements.

4. The method of claim 3, wherein each entry in the mapping table records an original frame information vector, and only if the frame information vector hits, the frame information vector hits in the query process, and otherwise the frame information vector is processed as a missing data frame.

5. The active identification and forwarding method for TSN-oriented mixed traffic of claim 1, wherein in step S2, tsn_tag insertion is implemented based on double_vlan technology.

6. The method for actively identifying and forwarding TSN-oriented traffic according to claim 5, wherein in step S2, the tsn_tag is defined by the location of the outer_vlan.

7. The method for actively identifying and forwarding TSN-oriented mixed traffic according to claim 1, wherein in step S2, tsn_tag is composed of 4 bytes, wherein the first two bytes are flow identification information, and the method is characterized by using an unused reserved field in an ethernet protocol type; the last two bytes are the stream ID, 16 bits total.

8. The method for actively identifying and forwarding TSN-oriented mixed traffic according to claim 1, wherein in the step S2, when the data stream is sent to the data output port of the switch, when the data frame in the data stream is written into the entry buffer module of the switch, the content in the data frame is synchronously extracted and parsed, and if tsn_tag is parsed, the forwarding table is queried according to the stream ID to obtain the data output port; the TSN_Tag is analyzed in the first clock period of the data frame written-in entry buffer module, inquiry is carried out in the second clock period, and an inquiry result is obtained in the third clock period; the ingress buffer module read operation begins a third clock cycle after the ingress buffer module write.

9. The method according to claim 1, wherein in the step S2, when forwarding the data stream from the data output port of the switch to the second controller, for each determined data output port, a data path between the data output port and all other ports is established, and the ST stream uses a time division multiplexing mode based on the global time to perform data transmission between the data output ports through the corresponding data path.

10. An active identification and forwarding system for TSN hybrid traffic is characterized by comprising:

the TSN controller includes:

the TSN switch includes: