WO2020119418A1 - Data processing method, apparatus and device, and storage medium - Google Patents

Abstract

Provided are a data processing method, apparatus and device, and a storage medium. The method comprises: an SA node cutting and marking a data packet sent by an input node to obtain at least one marked cell; sending the at least one marked cell to at least one switch node, and receiving at least one returned cell sent by the at least one switch node based on the at least one marked cell, wherein the returned cell is obtained after the at least one switch node switches the marked cells; unmarking and recombining the at least one returned cell to obtain a recombined data packet; and sending the recombined data packet to a target node.

Description

Data processing method, device, equipment and storage medium Technical field

The embodiments of the present application relate to the technical field of the Internet, and relate to, but are not limited to, a data processing method, device, equipment, and storage medium.

Background technique

With the increase in broadband demand and business scale, the industry has put forward higher requirements for the efficient transmission of data, and ensuring data stability in data transmission under high-rate channels is the key to achieving efficient data transmission. The current mainstream solution Designed for switching networks.

The existing switching network design uses cells as the basic unit for switching. Therefore, Switch Access (SA) nodes need to cut data packets into cells and send them to the switching network for switching. Then, after the cell reaches the destination, the cell needs to be reassembled into a complete data packet.

Due to the need to load-balance all cells of a data packet to different switching nodes, the delay of different cells passing through different switching nodes to reach their destination will be different. Without special processing, cells of the same data packet will arrive at the destination node out of order, and cells of different data packets will be interleaved together.

Summary of the invention

In view of this, embodiments of the present application provide a data processing method, device, device, and storage medium.

The technical solutions of the embodiments of the present application are implemented as follows:

In a first aspect, an embodiment of the present application provides a data processing method, which is applied to a data processing system. The system includes an SA node, an input node, a switching node, and a target node; the method includes:

The SA node cuts and marks the data packet sent by the input node to obtain at least one mark cell;

The SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein, the return letter The element is obtained after the at least one switching node exchanges the marked cells;

The SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet;

The SA node sends the reassembled data packet to the target node.

In other embodiments, the SA node cuts and marks the data packet sent by the input node to obtain at least one mark cell, including:

The SA node cuts the data packet to obtain at least one cell;

Adopting a preset label to mark each cell in the at least one cell to obtain the marked cell;

Wherein, the preset label includes at least one of the following: a destination identifier, a time identifier, a pseudo-mark identifier, and a type identifier.

In other embodiments, the method further includes:

Determine the type identifier of the corresponding cell according to the data version of the data packet;

Wherein, the data version of the data packet includes: unicast data packet and multicast data packet;

Correspondingly, the type identification includes: unicast and multicast.

In other embodiments, the pseudo mark identifier is used to hide the type identifier of the cell, and the method further includes:

Each of the marked cells is marked as a data cell through the pseudo-marked identification; wherein the pseudo-marked identification of each of the data cells is the same.

In other embodiments, the method further includes:

The SA node groups the returned cells according to the preset label of each returned cell to obtain at least one cell group;

Correspondingly, the SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet, including:

The SA node demarks the return cells in each cell group;

According to the time identifier of each return cell in each cell group, recombination processing is performed on the return cells after the de-marking process to obtain the reassembled data packet.

In other embodiments, the SA node groups the return cells according to the preset label of each return cell to obtain at least one cell group, including:

The SA node groups the return cells according to the destination identification and/or type identification in the preset label of each return cell to obtain at least one cell group.

In other embodiments, the method further includes:

When the data version of the data packet includes both a unicast data packet and a multicast data packet, the SA node selects a preset label corresponding to the unicast data packet according to a preset rule, and the multicast Among the preset labels corresponding to the data packets, determine the control labels;

Control the data transmission sequence of the unicast data packet and the multicast data packet according to the control label and the preset comparison label; and/or,

According to the control tag and the preset comparison tag, determine to delete the preset tag corresponding to the unicast data packet, or delete the preset tag corresponding to the multicast data packet.

In a second aspect, an embodiment of the present application provides a data processing apparatus, the apparatus including:

The first processing unit is configured to cut and mark the data packet sent by the input node to obtain at least one mark cell;

A first sending unit, configured to send the at least one marking cell to at least one switching node;

A receiving unit, configured to receive at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein, the returning cell is performed by the at least one switching node on the marking cell What you get after the exchange process;

The second processing unit is configured to perform unmarking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet;

The second sending unit is configured to send the reassembled data packet to the target node.

In a third aspect, an embodiment of the present application provides a data processing device, the device at least includes: a processor and a storage medium configured to store executable instructions, wherein: the processor is configured to execute the stored executable instructions;

The executable instruction is configured to perform the above data processing method.

According to a fourth aspect, an embodiment of the present application provides a storage medium in which computer-executable instructions are stored, and the computer-executable instructions are configured to perform the foregoing data processing method.

Embodiments of the present application provide a data processing method, device, device, and storage medium, where the method includes: the SA node cutting and marking a data packet sent by an input node to obtain at least one marking cell; The SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein, the returning cell It is obtained after the at least one switching node exchanges the marked cells; the SA node demarks and reassembles the at least one returned cell to obtain a reassembled data packet; the SA node Sending the reassembled data packet to the target node. In this way, since the SA node cuts and marks the data packet, the obtained mark cell has a preset label, then, when performing data exchange processing on the mark cell and returning to the destination node At the same time, all the marked cells can be distinguished according to the preset label, so as to ensure that different cells can reach the destination node in order, and can avoid the increase of new node resources to the greatest extent, thereby improving SA nodes Application efficiency reduces quality risks.

BRIEF DESCRIPTION

In the drawings (which are not necessarily drawn to scale), similar reference numbers may describe similar components in different views. Similar reference numerals with different letter suffixes may denote different examples of similar parts. The drawings generally illustrate various embodiments discussed herein by way of example and not limitation.

FIG. 1A is a schematic diagram of an implementation process of the data processing method provided in Embodiment 1 of the present application;

1B is a schematic structural diagram of a data processing system provided by an embodiment of this application;

2 is a schematic diagram of an implementation process of the data processing method provided in Embodiment 2 of the present application;

3 is a schematic diagram of an implementation process of the data processing method provided in Embodiment 3 of the present application;

4 is a schematic diagram of an implementation process of the data processing method provided in Embodiment 4 of the present application;

5 is a schematic structural diagram of the composition of an SA-IP node provided by an embodiment of this application;

6 is a schematic structural diagram of a marker cell provided by an embodiment of this application;

FIG. 7 is a schematic diagram of the structure of the tag label provided by the embodiment of the present application;

8A is a schematic structural diagram of a marker cell provided by an embodiment of this application;

8B is a schematic structural diagram of another marker cell provided by an embodiment of the present application;

9 is a sequence diagram of cells formed after cutting a data packet according to an embodiment of the present application;

10 is a schematic structural diagram of the composition of a data processing device provided by an embodiment of this application;

FIG. 11 is a schematic structural diagram of a data processing device provided by an embodiment of the present application.

detailed description

To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the specific technical solutions of the invention will be described in further detail in conjunction with the drawings in the embodiments of the present invention. The following examples are used to illustrate the present invention, but are not used to limit the scope of the present invention.

In the subsequent description, the use of suffixes such as "module", "part" or "unit" used to denote an element is only for the benefit of the description of the present application, and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.

The design of the switching network is based on the exchange of cells as the basic unit. The realization process is to cut the input data packets to form cells. For example, the SA node cuts the received data packets; then, the SA node Sending the formed cells to the switching node in the switching network, performing switching processing on the cells through the switching node, and sending the processed cells to the target node. After the cell reaches the target node, the target node reassembles the cell into a complete data packet.

In the current switching network design, since multiple cells corresponding to a data packet need to be sent to one or more switching nodes in the switching network, then when there are multiple switching nodes, the cells are exchanged through multiple nodes Processing, therefore, due to the unsynchronized processing of multiple nodes and the different timeliness of the processing of multiple nodes, it will cause the delay of the cell being sent to the target node after passing through multiple nodes. In other words, multiple cells cannot reach the target node in the order in which the cells were cut. In addition, when the SA node receives multiple data packets at the same time, the SA node will process the multiple data packets at the same time and send them to the switching node, so that there will be a message in multiple data packets. If the cells corresponding to multiple data packets are sent to the target node, and the target node combines the cells to form a data packet, you need to use the code analysis (Code Analysis) Mode (CAM) technology. Obviously, this will make the data processing process extremely complicated and require more SA nodes to meet the resource and performance requirements.

Based on the above-mentioned at least one problem in the related art, an embodiment of the present application provides a data processing method, which performs labeling processing on a cell through a preset label, and the labeling processing enables coordination of unicast packets and multicast packets Mark synchronization, so that different cells can reach the destination node in an orderly manner, and can ensure the coordinated and orderly transmission of different packet data, and realize an extremely perfect cell order preservation scheme.

Here, before introducing the data processing method of the embodiment of the present application, first introduce the data processing system applied in the present application. As shown in FIG. 1B, the data processing system includes an SA node 11, an input node 12, a switching node 13, and a target node 14.

Wherein, the SA node 11 is used to implement the data processing method of the present application, the input node 12 is used to input a data packet to the SA node 11, and the switching node 13 is used to perform a cell on the SA node 11 In the switching process, the target node 14 is used to receive the cell sent by the switching node 13 through the SA node 11.

In the embodiment of the present application, there may be one or more input nodes 12, one or more switching nodes 13, and one or more target nodes 14. The number of input nodes 12, switching nodes 13 and target nodes 14 can be set according to actual needs, and this embodiment is not limited.

FIG. 1A is a schematic diagram of an implementation process of a data processing method provided in Embodiment 1 of the present application. The method is applied to the data processing system shown in FIG. 1B. As shown in FIG. 1A, the method includes:

Step S101: The SA node cuts and marks the data packet sent by the input node to obtain at least one mark cell.

Here, the SA node includes a Receive (RC) processing module, a Transmit (TC) processing module, a Mathematics (MAC) processing module, and an Automatic Storage Management (ASM) processing module. The process in step S101 is implemented by the RC processing module. Therefore, step S101 can be implemented by the following steps:

Step S1011: The RC processing module in the SA node obtains the data packet sent by the input node.

Step S1012: The RC processing module performs cutting and marking on the data packet.

In this embodiment, the data packet may be any type of data packet, such as a unicast data packet or a multicast data packet.

There may be one or more data packets sent by the input node. When there are multiple data packets, the data packets may be data packets of the same version or data packets of different versions. This is not limited.

When there are multiple data packets, the RC processing module may simultaneously cut and mark multiple data packets, or the RC processing module may cut multiple data packets in sequence according to a preset order And tag processing.

In this embodiment, each of the marking cells carries a marking label, and the marking label is a preset label. The marked cell is obtained by performing a marking process on the cell formed by cutting the data packet. Through the tag label, the feature information of the tag cell can be identified, and then the cell can be distinguished.

In step S102, the SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell.

Here, the at least one switching node forms a switching network, and the switching network is used to implement exchange processing on cell data. The exchange processing may be any existing data processing process, which is not done in this embodiment. limited.

In this embodiment, the return cell is obtained after the at least one switching node exchanges the marked cell. When the at least one marking cell is sent to the switching network, at least one switching node in the switching network performs the switching process on the marking cell to obtain a processed cell, that is, the Return the cell, and return the returned cell to the SA node.

In this embodiment, the return cell contains the same tag label as the corresponding tag cell.

In an embodiment of the present application, after the switching node exchanges the marked cells to obtain the return cell, the MAC processing module in the SA node receives the return message sent by the switching node The MAC processing module then sends the return information to the TC processing module, so that the TC processing module performs corresponding processing on the at least one return cell.

Step S103: The SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet.

Here, the de-tagging process is used to de-tag the tag label in the return cell to form the return cell into an unlabeled cell. The de-marking process is a reverse process of the mark processing. The de-marking process does not change the cell information of the returned cell.

The reassembly process is used to combine the unlabeled cells to form a reassembled data packet.

In an embodiment of the present application, the arrangement order of all cells in the reassembled data packet may be the same as the arrangement order of all cells in the data packet sent by the input node, or, in the reassembled data packet The arrangement order of all the cells in has a preset association relationship with the arrangement order of all the cells in the data packet sent by the input node.

For example, when the arrangement order of all cells in the reassembled data packet has a preset association relationship with the arrangement order of all cells in the data packet sent by the input node, the association relationship may be in reverse order Relationships, or relationships arranged according to certain rules. The preset association relationship may be stored in the tag label, and when the SA node receives the return cell, the SA node may obtain the preset association relationship carried in the return cell, Then, the returned cells after the de-marking process are sorted based on the preset association relationship.

In an embodiment of the present application, the number of all cells in the reassembled data packet may be the same as or different from the number of cells in the data packet sent by the input node.

When the number of all cells in the reassembled data packet is different from the number of cells in the data packet sent by the input node, it may correspond to the following scenario: a data packet sent by the SA node to the input node Cut and mark to obtain M marked cells; the SA node sends M marked cells to multiple switching nodes, and multiple switching nodes mark the M marked cells to obtain N return letters Cell, and sends N return cells to the SA node; the SA node de-marks the N return cells to obtain N unlabeled cells, and the N unlabeled cells recombine to form the reorganization data pack. At this time, the number of all cells in the reassembled data packet is N, and the number of cells in the data packet sent by the input node is M, and M is not equal to N.

In an embodiment of the present application, after the MAC processing module in the SA node receives the return cell, the MAC processing module sends the return cell to the TC processing module, and the TC processing module Return the cells for de-marking; then, the TC processing module sends the unlabeled cells formed after the de-marking to the ASM processing module; the ASM processing module performs the reorganization processing on the unlabeled cells, To obtain the reassembled data packet.

Step S104: The SA node sends the reassembled data packet to the target node.

Here, the target node has a corresponding relationship with the sending node. When the sending node sends the data packet, the target node has been determined according to the data packet; or, the target node and the exchange The nodes have a corresponding relationship. When the switching node performs an exchange process on the marked cell, the target node has been determined according to the return cell formed by the exchange process.

In the data processing method provided in the embodiment of the present application, the SA node cuts and marks the data packet sent by the input node to obtain at least one marking cell; the SA node sends the at least one marking cell to at least one A switching node, and receiving at least one return cell sent by the at least one switching node based on the at least one marking cell; the SA node performs demarking processing and reassembly processing on the at least one return cell to obtain reorganization Data packet; the SA node sends the reassembled data packet to the target node. In this way, since the SA node cuts and marks the data packet, the obtained mark cell has a preset label. Then, when performing data exchange processing on the mark cell and returning to the target node Can identify and distinguish the marked cells according to the preset label, so as to ensure that different cells can reach the destination node in an orderly manner, and can avoid the increase of new node resources to the greatest extent, thereby improving The efficiency of SA node application reduces the quality risk.

FIG. 2 is a schematic diagram of an implementation process of a data processing method provided in Embodiment 2 of the present application. The data processing method is applied to a data processing system. The data processing system includes an SA node, an input node, a switching node, and a target node. As shown in FIG. 2, the data processing method includes the following steps:

In step S201, the SA node receives the data packet sent by the input node.

Here, there may be one or more input nodes, and there may be one or more data packets sent by the input node.

Step S202, the SA node cuts the data packet to obtain at least one cell.

Here, the SA node cutting the data packet may be cutting the data packet into cells with a preset length according to the attribute of the data packet. Each cell is composed of a header and an information segment. The header contains control information, and the information segment contains user information or other management information that is decomposed into data blocks.

It should be noted that when there are multiple data packets, the SA node cuts the multiple data packets to form at least two cells.

Step S203: Determine the type identifier of the corresponding cell according to the data version of the data packet.

Here, the data version of the data packet includes: unicast data packet and multicast data packet; or, the data version of the data packet includes time division multiplexing (Time Division Multiplexing, TDM) unicast data packet and TDM multicast data package.

When the SA node receives the data packet, the SA node obtains the data version of the data packet, and then determines the type identifier of the corresponding cell according to the data version, where the type identifier includes unicast And multicast; or the type identification includes TDM unicast and TDM multicast.

Step S204, using a preset label to mark each cell in the at least one cell to obtain the marked cell.

Here, the preset label includes at least one of the following: a destination identification, a time identification, a pseudo-mark identification, and a type identification.

The destination identification is used to record the input node identification (ID) and target node ID of the cell. Therefore, the input node and the target node of the corresponding cell can be quickly and accurately determined according to the target identifier in the preset label, thereby ensuring that the cell can be accurately transmitted to the target node during the transmission process.

The time identifier is used to mark the sending order of each cell when there are multiple cells. For example, in the process of data packet cutting, the cells obtained by cutting can be marked with a time mark in chronological order according to the cutting order, so that when the cell finally reaches the target node, it can be marked according to the time of each cell Reassembly to form a reassembled data packet with the same order as the original data packet.

The pseudo mark identifier is used to hide the data type of the cell, that is, all the cells of the data packet are marked with the same pseudo mark identifier, so that all the cells have the same data type, then In the transmission process of the cell, it will not distinguish the data types and use unused transmission paths, which can ensure that multiple types of data are transmitted simultaneously under the same conditions, thereby effectively saving available resources.

The type identification is determined according to the data version of the data packet sent by the input node, and the type representation of each cell is the same as the data version of the corresponding data packet. For example, when the data version of the data packet is a TDM unicast data packet, the type identifier of the cell is TDM unicast; when the data version of the data packet is a TDM multicast data packet, the cell The type identifier is TDM multicast. The type identifier is used to distinguish the type of the corresponding cell. In order to prevent multiple types of cells from interfering with different types of cells after reaching the target node at the same time.

In this embodiment, a preset label is used to mark each cell, which can be achieved by the following steps:

In step S2041, the SA node obtains attribute information of the data packet sent by the input node.

Here, the attribute information includes at least one of the following: the input node ID, the target node ID, the time when the input node sends the data packet, the time when the SA node receives the data packet, and the data version of the data packet.

Step S2042: Determine a preset label according to the attribute information.

In this embodiment, determining the preset label according to the attribute information may be: determining the destination identifier based on the input node ID and the target node ID; determining the time identifier based on the time when the input node sends the data packet and the time when the SA node receives the data packet ; Determine the type identification according to the data version of the data packet. Finally, the preset label is determined according to the determined destination identifier, time identifier, type identifier, and preset pseudo mark identifier.

Step S2043: Mark each cell according to the preset label to obtain the marked cell.

Here, the marking process may be carrying the preset label on the corresponding cell to form the marking cell. In this way, by detecting the preset tag carried in the marked cell, the attribute information of the corresponding cell can be obtained.

In step S205, the SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell.

Here, the return cell is obtained after the at least one switching node exchanges the marked cell.

In step S206, the SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet.

Step S207, the SA node sends the reassembled data packet to the target node.

It should be noted that steps S206 to S207 are the same as the above steps S103 to S104, and details are not described in this embodiment.

In the data processing method provided in the embodiment of the present application, the SA node cuts the data packet to obtain at least one cell; according to the data version of the data packet, determines the type identification of the corresponding cell; adopts a preset label, Marking is performed on each of the at least one cell to obtain the labeled cell; wherein, the preset label includes at least one of the following: a destination identification, a time identification, a pseudo-label identification, and a type identification. In this way, after labeling the cell with the preset label, a labeled cell with label attribute information can be obtained, then it can be ensured that when the corresponding cell returns to the destination node, the cell can be effectively identified and Differentiate, so as to ensure that different cells can reach the target node in an orderly manner, and multiple data packets and multiple types of data packets can be effectively processed through one SA node, so that new SA node resources can be avoided to the greatest extent Increase, thereby improving the efficiency of SA node applications and reducing quality risks.

FIG. 3 is a schematic diagram of an implementation process of a data processing method provided in Embodiment 3 of the present application. The data processing method is applied to a data processing system. The data processing system includes an SA node, an input node, a switching node, and a target node. As shown in FIG. 3, the data processing method includes the following steps:

Step S301: The SA node cuts the data packet to obtain at least one cell.

It should be noted that step S301 is the same as step S202 described above, and details are not described in this embodiment.

Step S302, using a preset label to mark each cell in the at least one cell to obtain the marked cell.

Here, the preset label includes at least one of the following: a destination identification, a time identification, a pseudo-mark identification, and a type identification.

Wherein, the pseudo mark identifier is used to hide the type identifier of the cell, so that, as a whole, multiple cells of different types have the same type. Therefore, multiple different types of cells Cells are sent and processed at the same time to greatly reduce latency.

Step S303: Mark each label cell as a data cell by using the pseudo label identifier.

Here, the pseudo mark identifier is used to mark each mark cell as a data cell. In this way, when the mark cell is transmitted to the switching node, all the cells reflect the data type to the outside. Transmit at the same time without distinguishing between data and messages. In this embodiment, each of the data cells has the same pseudo mark identifier, that is, the types of the marked cells after being marked by the pseudo mark identifier are the same.

Step S304, the SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell.

Here, the return cell is obtained after the at least one switching node exchanges the marked cell.

In step S305, the SA node groups the returned cells according to the preset label of each returned cell to obtain at least one cell group.

Here, since the preset label includes at least one of the following: a destination identification, a time identification, a pseudo-mark identification, and a type identification. Wherein, the destination identifier includes an input node ID and a target node ID; the type identifier includes unicast and multicast, or the type identifier includes TDM unicast and TDM multicast. Then, grouping the return cells in step S305 can be implemented in the following three ways:

Manner 1: Group the returned cells according to the destination identifier in the preset label of each returned cell to obtain at least one cell group.

Here, the destination identification includes the input node ID and the target node ID. Therefore, all return cells can be grouped according to the input node ID and/or the target node ID, and the returns having the same input node ID and/or the same target node ID can be returned. The cells are divided into a cell group.

Manner 2: According to the type identifier in the preset label of each returned cell, group the returned cells to obtain at least one cell group.

Here, the type identifier includes unicast and multicast, or the type identifier includes TDM unicast and TDM multicast, therefore, it can be determined whether the type identifier in the return node is unicast or multicast, or the Whether the type identifier is TDM unicast or TDM multicast, the return nodes with the same type identifier are divided into the same cell group.

Manner 3: According to the destination identifier and the type identifier in the preset label of each returned cell, group the returned cells to obtain at least one cell group.

Here, the destination identifier includes the input node ID and the target node ID, and the type identifier includes unicast and multicast, or the type identifier includes TDM unicast and TDM multicast, therefore, the same destination identifier and the same type identifier can be returned Nodes are divided into the same cell group.

In step S306, the SA node demarks the return cells in each cell group.

Here, the de-tagging process is used to de-tag the tag label in the return cell to form the return cell into an unlabeled cell. The de-marking process is a reverse process of the mark processing. The de-marking process does not change the cell information of the returned cell.

Since each cell group includes return nodes with the same destination identification and/or the same type identification, it is possible to perform the de-marking process in the unit of the cell group, and perform the simultaneous removal of all the return cells in one cell group Mark processing.

Step S307, according to the time identifier of each return cell in each cell group, perform reassembly processing on the return cell after the de-marking process to obtain the reassembled data packet.

Here, after de-marking each return cell, the time identifiers of all return cells in each cell group are determined, and according to the order of time identifiers of all return cells, all un-marked The return cells are sorted, and the unmarked return cells are recombined according to the sorting order to obtain the reassembled data packet.

In step S308, the SA node sends the reassembled data packet to the target node.

The data processing method provided in this embodiment of the present application uses a pseudo mark to hide the type identification of the cell, so that multiple cells of different types, as a whole, have the same type. Therefore, you can Multiple cells of different types are sent and processed at the same time to greatly reduce latency. In addition, the preset label includes a time identifier. Therefore, when the return cells are reorganized, all the return cells can be sorted according to the time labels, and the unmarked return cells can be reorganized according to the sorting order After processing, the reassembled data packet is obtained. In this way, the arrangement order of the cells in the reassembled data packet can be ensured to be consistent with the arrangement order of the cells in the data packet sent by the input node, thereby ensuring the orderly transmission of the cells.

4 is a schematic diagram of an implementation process of a data processing method provided in Embodiment 4 of the present application. The data processing method is applied to a data processing system, and the data processing system includes an SA node, an input node, a switching node, and a target node. As shown in FIG. 4, the data processing method includes the following steps:

Step S401: The SA node cuts the data packet to obtain at least one cell.

Step S402: Determine the type identifier of the corresponding cell according to the data version of the data packet.

Here, the data version of the data packet includes: unicast data packet and multicast data packet; the type identification of the cell includes: unicast and multicast.

In step S403, a preset label is used to mark each cell in the at least one cell to obtain the marked cell.

Here, the preset label includes at least one of the following: a destination identification, a time identification, a pseudo-mark identification, and a type identification.

Step S404, the SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell.

Here, the return cell is obtained after the at least one switching node exchanges the marked cell.

Step S405: When the data version of the data packet includes both a unicast data packet and a multicast data packet, the SA node determines a control label according to a preset rule.

It should be noted that this embodiment is performed after the ASM processing module in the SA node receives the return cell.

Here, when the data version of the data packet sent by the input node includes both a unicast data packet and a multicast data packet, or when there are multiple data packets and the data versions of the multiple data packets are different, the SA node The ASM processing module in determines the control label from the preset label corresponding to the unicast data packet and the preset label corresponding to the multicast data packet according to a preset rule, or the SA node The preset rule determines the control tag among the preset tags corresponding to multiple data packets.

Step S406: Control the data transmission sequence of the unicast data packet and the multicast data packet according to the control label and the preset comparison label.

Here, the preset contrast label is a label preset by the system, and the preset contrast label may be adjusted according to service needs.

In this embodiment, the relationship between the control tag and the preset comparison tag is determined, and the transmission order of the cells of the corresponding data packet is determined according to the determination result.

For example, the size of the time tag in the control tag and the time tag in the preset comparison tag can be determined, and when the time tag in the control tag is greater than the time tag in the preset comparison tag, If the data packet corresponding to the control label is a multicast data packet, the cells of the multicast data packet are controlled to be transmitted preferentially.

Step S407, according to the control tag and the preset comparison tag, determine to delete the preset tag corresponding to the unicast data packet, or delete the preset tag corresponding to the multicast data packet.

In this embodiment, the relationship between the control tag and the preset comparison tag is determined, and whether to delete the preset tag corresponding to the cell of the data packet is determined according to the determination result.

For example, the size of the time tag in the control tag and the time tag in the preset comparison tag can be determined, and when the time tag in the control tag is greater than the time tag in the preset comparison tag, If the data packet corresponding to the control label is a multicast data packet, the preset label corresponding to the cell of the multicast data packet is deleted.

Step S408: The SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet.

Step S409: The SA node sends the reassembled data packet to the target node.

It should be noted that steps S408 to S409 are the same as the above steps S103 to S104, and details are not described in this embodiment.

According to the data processing method provided in the embodiment of the present application, when the data version of the data packet includes both a unicast data packet and a multicast data packet, the SA node determines a control label according to a preset rule; according to the control label and Preset comparison tags to control the data transmission sequence of the unicast data packets and the multicast data packets, and/or determine to delete the preset tags corresponding to the unicast data packets and the multicast data packets One of the preset labels can avoid the risk that the preset labels of the unicast data packet guarantee cell receiving order and the multicast data packet guarantee cell receiving order may be inconsistent.

Based on the above embodiments, the embodiments of the present application further provide a data processing method, so that unicast data packets and multicast data packets can perform mark synchronization in a more coordinated manner, thereby implementing an extremely perfect order preserving scheme that guarantees the receiving order of cells. Solve the problem that different cells may reach the target node out of order; and, because there is no simultaneous use of the TDM plane and the single multicast plane, the two are equivalent to mutual exclusion, multiplexing the resources of the marking plane, including statistics , Logic, configuration, etc., to avoid the increase of new resources to the greatest extent, thereby improving the efficiency of node applications and reducing quality risks.

The data processing method provided in the embodiments of the present application includes an integrated multiplexing label and synchronous coordination of multiplexing labels for unicast and multicast.

The data processing method is completed by an SA-IP node predefined by the protocol (that is, the SA node described above). As shown in FIG. 5, it is a schematic structural diagram of the composition of the SA-IP node provided by an embodiment of the present application. Among them, the SA-IP node 50 is mainly composed of the following four modules: RC processing module 51; TC processing module 52; MAC processing module 53; ASM processing module 54. The main function of the RC processing module is to cut data cells and mark and label the cells; the main function of the TC processing module is to restore the cells and remove the labels; the ASM processing module is mainly set to reorganize the cells; The MAC module is responsible for supporting 36 high-speed serses links.

In this embodiment, the synchronization coordination process of multiplexing tags for unicast and multicast, the unicast (including unicast and multicast) processing path of the RC processing module on the sending side is unchanged, and the RC processing module converts the TDM plane Flow control (including internal label flow control) also acts on the unicast transmission plane, so that the label counts of the two planes are exactly the same. The transmission label is loaded using the unicast label as the TDM label.

As the TC processing module on the receiving side, the received version cells are separated into unicast and multicast marking planes, so that ASM basically does not need to be modified. The single multicast plane flow control generated by ASM is simultaneously merged into the TDM plane.

The method of this embodiment guarantees the normalization of SA-IP timing at the level of the labeling scheme, and by initializing strict RC transmission and TC reception side timing control constraints, the optimal link adaptation state and the convergence of the code stream are achieved , To ensure the accuracy and stability of the link quality.

This embodiment takes the SA node as an SA chip as an example for description. In the data processing method provided in this embodiment, the cells formed after the data packet is cut are marked with a label to form a label cell. As shown in FIG. 6, it is a schematic structural diagram of the label cell provided in this embodiment. The data packet is cut into four cells A, B, C, and D in the SA chip, and each cell is labeled with a label 61 and a label 62, where the label of A is 0 and the label of B is 1, C The mark of is 2, the mark of D is 3, and finally, the marked cells are sent to the target chip 63.

7 is a schematic diagram of the composition structure of a tag label provided by an embodiment of the present application. As shown in FIG. 7, the data cell 71 and the tag label together form a tag cell, where the tag label includes a destination tag 72, a time tag 73, and a pseudo Marker mark 74 and type mark 75.

Among them, the destination mark is mainly used to record the source chip ID (that is, the above-mentioned input node ID) and the target chip ID. Time stamps are mainly used to confirm the order in which different cells are sent out. Pseudo mark identification, to show whether a pseudo type mark is used. Type tags are mainly divided into four categories: unicast, multicast, TDM unicast, and TDM multicast.

8A is a schematic structural diagram of a marking cell provided by an embodiment of the present application, and FIG. 8B is a schematic structural diagram of another marking cell provided by an embodiment of the present application. As shown in FIGS. 8A and 8B, the structure of the marking cell Includes two parts of information (WORD1 and WORD1). The two parts of the marked cell include the cell type (TYPE), version (VER), packet size (PACKET_SIZE), source chip ID (SRC_SA_ID), Target chip information (FABRIC_DEST_INFO).

In addition, it should be noted that the numbers "332222222222111111111198"1098765432109876543210" and "210" located at the upper part of the marking cell are codes of the marking cell, and are used to identify the marking cell.

The upper part of Fig. 8A shows the structure of the mark cell, and the lower part of Fig. 8A shows the structure of the mark chip of type 2'B00. As shown in FIG. 8A, the 2'B00 marked cell is a multicast type, so the corresponding target chip is a multicast chip ID (MULTICAST_ID).

Fig. 8B shows the structure of a marked cell of type 2'B01, and the exit nodes of the marked cell are OUT_PORT[7:0] and OUT_PORT[9:8], respectively.

In the embodiment of the present application, the single multicast and TDM planes can be combined based on the above multiplexing label scheme. In this merger scheme, the RC processing module, TC processing module, MAC processing module, and ASM processing module perform different actions, respectively.

Among them, the RC processing module is set to configure version 3 (where version 3 is a version type with unicast, multicast, TDM unicast, and TDM multicast), and the unicast and multicast data flow processing paths remain unchanged. The loading place loads the TDM mark derived from the Unicast Time Stamp (UTS) packet. And the processing of UTS and multicast timestamp (Multicast Time Stamp, MTS) must be consistent, that is, whether it is TDM unicast or TDM multicast, UTS and MTS are locked.

In addition, in the cells sent through the link provided by the MAC processing module, when the unicast validity time (Unicast Time Valid, UTV) and the multicast validity time (Multicast Time Valid, MTV) remain at 0, and deputy When the tags are loaded alternately, the cell header mainly carries two tag fields, one is the TDM Time Stamp (OTS) tag field, which is always carried, and the other field is determined by the content passed. That is, when UTV is 0, the cell header carries the UTS tag field, and when MTV is 0, the cell header carries the MTV tag field, and the two fields alternately contain bands.

9 is a sequence diagram of cells formed after cutting a data packet according to an embodiment of the present application. As shown in FIG. 9, under conventional conditions, within a preset period (the circle of the circle in the figure is a preset) (Period), the data packet is cut into cells 91, 92, 93, where cell 91 is the oldest cut cell, so after cell 91 is marked, the cell has the oldest tag. Under the time stamp overflow condition, multiple cells 94, 95, 96 are formed within a preset period. It can be seen from FIG. 9 that due to the timestamp overflow, for multiple cells, it is impossible to determine which cell is the earliest cut cell, so that when marking multiple cells, it is also impossible to determine which The cell is marked for the oldest.

Based on the above-mentioned problems in cutting cells under the time stamp overflow condition, in this embodiment, if it is the delayed transmission count after the link transmission time stamp (Time Stamp, TV) is pulled high, this part of the logic is repeated use. It is worth noting that after each version configuration switch is completed, the status of sending the delay count (including unicast and multicast) will be rolled back, that is, the link tags link_UTV (=link_OTV) and link_MTV generated here will be temporarily pulled. low. The scheduling state machine for link selection does not need to be modified, and the response of the local flow control has not changed. Finally, link label extraction on the link. For version 3 cells, the TDM label is extracted to the link labels UTS_link and MTS_link at the same time. Thus, internal tag flow control can be generated correctly.

In statistical processing, for the statistics of the sent tags, TDM Time (Valid) (OTV) and OTS can be listed separately, but the resources are not increased, and the existing resources are reused. For the detection of out-of-order tags, TDM tags are also listed separately, but multiplexed on statistical resources. The statistics of the sent cells are not modified.

The TC processing module is set to copy the TDM tag fields (including OTV, OTS, O_SRC_ID, O_SEQ) in the tag information to unicast tags and multicast tags and send them to ASM. For TDM unicast cells, the type remains unchanged. The unicast tag field and the multicast tag field sent to ASM are filled with the TDM tag field. For TDM multicast cells, the type remains unchanged, and the unicast tag field and multicast tag field sent to ASM are filled with the TDM tag field. For empty cells, the type remains unchanged, and the unicast and multicast tag fields sent to ASM are filled with TDM tag fields. If a unicast/multicast data cell is received, it is defined as illegal and discarded after the report is interrupted.

In the statistical processing, for the statistical multiplexing of TDM cells, the statistical method of single multicast cells, TDM unicast multiplexing unicast, TDM multicast multiplexing multicast.

The MAC processing module not only supports version 0 (where version 0 is a version type with unicast and multicast) cells, but also supports version 3 cells. The MAC processing module adds extraction and statistics of TDM link and tag flow control.

The ASM processing module adds a new configuration. If the configuration is in the version 3 cell acceptance mode, the unicast oldest tag is compared with the multicast oldest tag to obtain the unique oldest tag, which is used to control the generation of tag flow control And mark deletion.

Here, the oldest mark refers to the earliest mark among multiple cells. In this embodiment, determining the unique oldest mark may be comparing the unicast oldest mark with the multicast oldest mark, determining the smallest mark as the unique oldest mark, or selecting the one that meets the preset condition One oldest mark is the only oldest mark. The preset condition is determined according to actual needs, and this embodiment is not limited.

In this embodiment, the modification of the mark flow control is because the oldest mark of unicast order preservation and multicast order preservation may be inconsistent, so there is a risk. In order to avoid risks, the tag flow control needs to be modified. Among them, the risk is that one of the oldest unicast mark and the oldest multicast mark will be deleted, and one will not be deleted. The following explains the possible conditions:

Case 1: If the oldest mark of a unicast is 10, the oldest mark of a multicast is 5, and the mark inserted in the two oldest marks is 100, obviously, the inserted mark 100 far exceeds 10 and 5. Assuming the deletion threshold of the oldest mark is 95, then 100 is backpressured against 10 and 100 is deleted against 5. If 100 comes from a newly inserted SA chip, since the SA has a backpressure reset or backpressure low link transmission TV function, you can try to join again. The 100 will not come from the newly inserted Switch Fabric (SF) chip. This is because the existing chip in the entire network can control the source tag to a certain range, which is definitely higher than the oldest tag of any ASM. In the half circle, the mark of the inserted SF chip comes from the source SA chip, and it is impossible to reach the deletion threshold with the oldest mark of an ASM.

Here, the backpressure refers to who has priority to send between the cell of the inserted SA chip and the cell corresponding to the oldest mark, that is, if the mark of the inserted SA chip is the oldest mark of unicast In case of back pressure, the cells of the unicast data are preferentially sent. After the cells of the unicast data are sent, the cells of the inserted SA chip are sent again.

Case 2: The inserted mark is between the two oldest marks. This situation is more common, for example, the two oldest marks are 5 and 10, and the inserted mark is 8, then for 10, this inserted mark is deleted. If 8 does not receive the back pressure of 5, after 8 advances to more than 10, this state can be released. However, the problem is that the gap between 10 and 5 will not be ruled out. Theoretically, in the switched network, the maximum value of the mark transition is around a mark backpressure threshold, so the two oldest marks may be quite different, so that the added mark is deleted relative to 10, relative to 5 is counter-pressure. Since they all come from the same link, this link will be back-pressured, and the tag cannot be updated to lock up.

Based on the above two situations, it can be seen that since there may be a backpressure or deletion between the two oldest marks and the inserted mark, the two oldest marks need to be unified, that is, the One unique oldest mark is determined from the two oldest marks.

The data statistics method provided by the embodiment of the present application solves the problem that different cells may reach the target node out of order. In addition, since there is no simultaneous use of the TDM plane and the single multicast plane, the two are equivalent to mutual exclusion. Multiplexing the resources of the marking plane, including statistics, logic, configuration, etc., in this embodiment of the present application can avoid new ones to the greatest extent. The increase in resources will increase the efficiency of chip applications and reduce quality risks.

Based on the foregoing embodiments, the embodiments of the present application provide a data processing apparatus including the included units and the modules included in the units, which can be implemented by a processor in a data processing device; Realized by logic circuit; in the implementation process, the processor may be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP) or a field programmable gate array (FPGA), etc.

FIG. 10 is a schematic structural diagram of a data processing device provided by an embodiment of the present application. As shown in FIG. 10, the data processing device 1000 includes:

The first processing unit 1001 is configured to cut and mark the data packet sent by the input node to obtain at least one mark cell;

The first sending unit 1002 is configured to send the at least one marking cell to at least one switching node;

The receiving unit 1003 is configured to receive at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein the returning cell is the at least one switching node to the marked cell What is obtained after the exchange process;

The second processing unit 1004 is configured to perform demarking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet;

The second sending unit 1005 is configured to send the reassembled data packet to the target node.

In other embodiments, the first processing unit includes:

A cutting module, configured to cut the data packet to obtain at least one cell;

A labeling module, configured to use a preset label to mark each cell in the at least one cell to obtain the labeled cell; wherein the preset label includes at least one of the following: a destination identification, Time mark, pseudo mark mark and type mark.

In other embodiments, the apparatus further includes: a first determining unit configured to determine the type identifier of the corresponding cell according to the data version of the data packet; wherein the data version of the data packet includes: unicast data Packets and multicast data packets; correspondingly, the type identifiers include: unicast and multicast.

In other embodiments, the pseudo mark identifier is used to hide the type identifier of the cell, and the device further includes: a marking unit configured to mark each marked cell as a data cell through the pseudo mark identifier ; Wherein, the pseudo-tag identification of each of the data cells is the same.

In other embodiments, the apparatus further includes: a grouping unit configured to group the returned cells according to a preset label of each returned cell to obtain at least one cell group; correspondingly, the first The second processing unit includes:

The de-marking module is set to de-mark the return cells in each cell group;

The reassembly module is configured to perform reorganization processing on the returned cells after the de-marking process according to the time identifier of each returned cell in each cell group to obtain the reassembled data packet.

In other embodiments, the grouping unit includes: a grouping module configured to group the returned cells according to the destination identifier and/or type identifier in the preset label of each returned cell to obtain at least one message Tuple.

In other embodiments, the device further includes:

The second determining unit is configured to, when the data version of the data packet includes both a unicast data packet and a multicast data packet, the SA node selects a preset label corresponding to the unicast data packet according to a preset rule , And the preset label corresponding to the multicast data packet determines the control label;

A control unit configured to control the data transmission sequence of the unicast data packet and the multicast data packet according to the control label and the preset comparison label; and/or according to the control label and the preset comparison label, It is determined to delete the preset label corresponding to the unicast data packet, or delete the preset label corresponding to the multicast data packet.

It should be noted that, in the embodiments of the present application, if the above data processing method is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention can be embodied in the form of software products in essence or part of contributions to related technologies. The computer software products are stored in a storage medium and include several instructions to make A terminal executes all or part of the methods described in various embodiments of the present invention. The foregoing storage media include various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (Read Only Memory, ROM), a magnetic disk, or an optical disk. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

Correspondingly, an embodiment of the present application provides a data processing device. FIG. 11 is a schematic structural diagram of the composition of the data processing device provided in the embodiment of the present application. As shown in FIG. 11, the data processing device 1100 at least includes: a processor 1101 , A communication interface 1102 and a storage medium 1103 configured to store executable instructions, wherein:

The processor 1101 generally controls the overall operation of the data processing device 1100.

The communication interface 1102 can enable the data processing device to communicate with other terminals or servers through a network.

The storage medium 1103 is configured to store instructions and applications executable by the processor 1101, and can also cache data to be processed or processed by the modules in the processor 1101 and the data processing device 1100, and can be accessed through flash memory (FLASH) or random access memory (Random Access Memory, RAM) implementation.

It should be understood that “one embodiment” or “one embodiment” mentioned throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present invention. Therefore, “in one embodiment” or “in one embodiment” appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present invention, the size of the sequence numbers of the above processes does not mean that the execution order is sequential, and the execution order of each process should be determined by its function and inherent logic, and should not correspond to the embodiments of the present invention. The implementation process constitutes no limitation. The sequence numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

It should be noted that in this article, the terms "include", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, It also includes other elements that are not explicitly listed, or include elements inherent to such processes, methods, objects, or devices. Without more restrictions, the element defined by the sentence "include one..." does not exclude that there are other identical elements in the process, method, article or device that includes the element.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a division of logical functions. In actual implementation, there may be other division methods, such as: multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components may be through some interfaces, and the indirect coupling or communication connection of the device or unit may be electrical, mechanical, or other forms of.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, the functional units in the embodiments of the present invention may all be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above integration The unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

Those of ordinary skill in the art may understand that all or part of the steps to implement the above method embodiments may be completed by program instructions related hardware. The foregoing program may be stored in a computer-readable storage medium. When the program is executed, the execution includes The steps of the above method embodiments; and the foregoing storage medium includes various media that can store program codes, such as a mobile storage device, a read-only memory (Read Only Memory, ROM), a magnetic disk, or an optical disk. Alternatively, if the above integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention can be embodied in the form of software products in essence or part of contributions to related technologies. The computer software products are stored in a storage medium and include several instructions to make A terminal executes all or part of the methods described in various embodiments of the present invention. The foregoing storage media include various media that can store program codes, such as a mobile storage device, a ROM, a magnetic disk, or an optical disk.

The above is only an embodiment of the present invention, but the scope of protection of the present invention is not limited to this, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present invention, should Covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Industrial applicability

As described above, a data processing method, device, device, and storage medium provided by embodiments of the present invention have the following beneficial effects: Since the SA node cuts and marks the data packet, the obtained marked cell has a preset label Then, when performing data exchange processing on the marked cells and returning to the destination node, the marked cells can be distinguished according to the preset label, so as to ensure that different cells can reach the destination node in an orderly manner, and can be maximized To avoid the increase of new node resources, thereby improving the efficiency of SA node applications and reducing quality risks.

Claims (10)

1. A data processing method is applied to a data processing system. The system includes a switch access SA node, an input node, a switch node, and a target node; the method includes:

   The SA node cuts and marks the data packet sent by the input node to obtain at least one mark cell;

   The SA node sends the at least one marking cell to at least one switching node, and receives at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein, the return letter The element is obtained after the at least one switching node exchanges the marked cells;

   The SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet;

   The SA node sends the reassembled data packet to the target node.
2. The method according to claim 1, wherein the SA node cutting and marking the data packet sent by the input node to obtain at least one marking cell includes:

   The SA node cuts the data packet to obtain at least one cell;

   Adopting a preset label to mark each cell in the at least one cell to obtain the marked cell;

   Wherein, the preset label includes at least one of the following: a destination identifier, a time identifier, a pseudo-mark identifier, and a type identifier.
3. The method of claim 2, wherein the method further comprises:

   Determine the type identifier of the corresponding cell according to the data version of the data packet;

   Wherein, the data version of the data packet includes: unicast data packet and multicast data packet;

   Correspondingly, the type identification includes: unicast and multicast.
4. The method according to claim 2, wherein the pseudo mark identification is used to hide the type identification of the cell, and the method further comprises:

   Each of the marked cells is marked as a data cell through the pseudo-marked identification; wherein the pseudo-marked identification of each of the data cells is the same.
5. The method of claim 2, wherein the method further comprises:

   The SA node groups the returned cells according to the preset label of each returned cell to obtain at least one cell group;

   Correspondingly, the SA node performs de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet, including:

   The SA node demarks the return cells in each cell group;

   According to the time identifier of each return cell in each cell group, recombination processing is performed on the return cells after the de-marking process to obtain the reassembled data packet.
6. The method according to claim 5, wherein the SA node groups the return cells according to a preset label of each return cell to obtain at least one cell group, including:

   The SA node groups the return cells according to the destination identification and/or type identification in the preset label of each return cell to obtain at least one cell group.
7. The method of claim 3, wherein the method further comprises:

   When the data version of the data packet includes both a unicast data packet and a multicast data packet, the SA node selects a preset label corresponding to the unicast data packet according to a preset rule, and the multicast Among the preset labels corresponding to the data packets, determine the control labels;

   Control the data transmission sequence of the unicast data packet and the multicast data packet according to the control label and the preset comparison label; and/or,

   According to the control tag and the preset comparison tag, determine to delete the preset tag corresponding to the unicast data packet, or delete the preset tag corresponding to the multicast data packet.
8. A data processing device, the device includes:

   The first processing unit is configured to cut and mark the data packet sent by the input node to obtain at least one mark cell;

   A first sending unit, configured to send the at least one marking cell to at least one switching node;

   A receiving unit, configured to receive at least one return cell sent by the at least one switching node based on the at least one marking cell; wherein, the returning cell is performed by the at least one switching node on the marking cell What you get after the exchange process;

   A second processing unit configured to perform de-marking processing and reassembly processing on the at least one return cell to obtain a reassembled data packet;

   The second sending unit is configured to send the reassembled data packet to the target node.
9. A data processing device, the device at least includes: a processor and a storage medium configured to store executable instructions, wherein: the processor is configured to execute the stored executable instructions;

   The executable instruction is configured to execute the data processing method provided in any one of claims 1 to 7 above.
10. A storage medium in which computer-executable instructions are stored, the computer-executable instructions being configured to perform the data processing method provided in any one of claims 1 to 7 above.

Images