WO2017097201A1

WO2017097201A1 - Data transmission method, transmission device and receiving device

Info

Publication number: WO2017097201A1
Application number: PCT/CN2016/108902
Authority: WO
Inventors: 林俊如; 何健飞
Original assignee: 华为技术有限公司
Priority date: 2015-12-09
Filing date: 2016-12-07
Publication date: 2017-06-15
Also published as: CN106856457A; CN106856457B

Abstract

Provided in the present application are a data transmission method, transmission device and receiving device, facilitating reduction of delay caused by timeout retransmission and task completion duration. The method comprises: a transmitting end acquires a first packet in a data stream, said first packet being a packet in which a first identifier is added to a second packet, the first identifier being used to identify the second packet as one of N packets, said N packets being a number N of packets before completion of transmission of the data stream, and N being greater than 0 and less than the number of packets of the data stream; the transmitting end transmits the first packet to a receiving end. The receiving end receives the first packet from the transmitting end and processes the first packet according to a packet transmission policy, and the packet transmission policy comprises a processing method to be performed on the first packet.

Description

Data transmission method, transmitting device and receiving device

This application claims the priority of the Chinese Patent Application filed on Dec. 9, 2015, the Chinese Patent Application No. CN201510906934.6, entitled "A Data Transmission Method, Transmission Device, and Receiving Device", the entire contents of which are hereby incorporated by reference. The citations are incorporated herein by reference.

Technical field

The present invention relates to the field of communications technologies, and in particular, to a data transmission method, a transmitting device, and a receiving device.

Background technique

The Transmission Control Protocol (TCP) is a connection-oriented, reliable, byte stream-based transport layer communication protocol. During the TCP transmission process, when the packet in the middle of the TCP stream is lost, the subsequent packet transmission can trigger fast retransmission, so that the sender can retransmit the lost packet in time.

If the lost packet is located at the end of the TCP stream, no subsequent packets trigger fast retransmission. Only the Retransmission Timeout (RTO) triggers the retransmission. RTO is a type of TCP operation timer. To prevent packet loss, when TCP sends a message, it starts the retransmission timer. However, the timer timeout period depends on the round trip time (RTT), which causes a large delay in the timeout retransmission, which prolongs the completion time of the task and reduces the user experience.

Summary of the invention

The embodiment of the invention provides a data transmission method, a sending device and a receiving device, which help to reduce the delay caused by timeout retransmission and the completion time of the task.

A first aspect of the embodiments of the present invention provides a data transmission method, including:

The sending end obtains the first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N. Messages in the message, The N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets of the data stream; the sending end sends the first packet to the receiving end.

In the embodiment of the present invention, the first packet is obtained by adding the first identifier to the second packet, and the first identifier is used to identify the first packet. The N packets before the transmission are completed for the data stream, and the first packet is sent to the receiving end. Therefore, when the data stream is sent, the transmitting end can identify the N packets before the data stream is transmitted.

With reference to the first aspect, in a first possible implementation manner of the first aspect, the obtaining, by the sending end, the first packet in the data stream includes:

The sending end determines, according to the second identifier carried in the second packet, that the second packet belongs to the N packets, and the second identifier is used to identify the second packet in the data. a location in the stream; the sender adds the first identifier to the second packet, and obtains the first packet.

With reference to the first aspect, or the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the first identifier is carried in the DCP of the first packet. a field; or the first identifier is carried in an option number field of the first packet.

In conjunction with the second possible implementation of the first aspect, in a third possible implementation of the first aspect, the first identifier may be an identifier on the 5th bit of the DSCP field.

In conjunction with the second possible implementation of the first aspect, in a fourth possible implementation of the first aspect, the first identifier may be a predetermined number in an option number field.

A second aspect of the embodiments of the present invention provides a data transmission method, including:

The receiving end receives the first packet from the sending end, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N The message in the message, the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the number of packets in the data stream; The first packet is processed according to the packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.

In the embodiment of the present invention, after receiving the first packet with the first identifier from the sending end, the receiving end processes the first packet according to the processing manner adopted by the first packet in the packet transmission policy. Process it. It can be seen that the receiving end processes the processing mode of the packet carrying the first identifier, and does not carry The processing of the packet with the first identifier is different. Therefore, the processing mode is more flexible, and the requirement for reducing the packet loss rate of the N packets before the data stream is completed is reduced, thereby reducing the transmission of the data stream. The timeout retransmission caused by the loss of the first N packets shortens the task completion time.

With reference to the second aspect, in a first possible implementation manner of the second aspect, the receiving, by the receiving end, processing the first packet according to a packet transmission policy,

The receiving end preferentially discards the received packet that does not carry the first identifier after the received packet queue corresponding to the data stream exceeds the first threshold. In the embodiment of the present invention, when the packet queue corresponding to the received data stream exceeds the first threshold, for example, when the network device needs to discard the packet due to congestion or traffic restriction, the device does not carry the packet. The packet of the first identifier is used to reduce the packet loss rate of the N packets before the data stream carrying the first identifier is completed.

With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the receiving end preferentially discarding the received packet that does not carry the first identifier includes:

The receiving end obtains a first parameter according to the first identifier and the corresponding relationship, where the corresponding relationship includes the first identifier and the first parameter, where the first parameter includes a second threshold and a discarding probability, where The drop probability is used to indicate the percentage of the operation of discarding the message; the receiving end receives the carried port according to the discard probability after the received message queue corresponding to the data stream exceeds the second threshold. The packet with the first identifier is discarded. In the embodiment of the present invention, the first packet carrying the first identifier has a higher second threshold and a lower discarding probability than the packet that does not carry the first identifier, thereby reducing the first packet. Packet loss rate.

With reference to the second aspect, in a third possible implementation manner of the second aspect, the receiving, by the receiving end, processing the first packet according to the packet transmission policy includes:

The receiving end copies the first packet, and obtains the M first packets, where the M is an integer greater than or equal to 2; the receiving end sends the M first packets Send to the wireless terminal. In the embodiment of the present invention, the M packets are sent to the wireless terminal, the packet loss rate of the first packet is reduced, and the packet transmitted before the first packet in the data stream is used. If the M message is successfully transmitted, the receiving end receives the confirmation message returned by the wireless terminal. After that, the receiving end can trigger the retransmission of the lost packet by fast retransmission to avoid the occurrence of timeout retransmission.

With reference to the third possible implementation of the second aspect, in a fourth possible implementation manner of the second aspect, the M is a value determined according to a default value of the number of copies of the message; or the M is The number of accesses is the number of wireless terminals that have accessed the receiving end according to the number of accesses and/or the value determined by the link quality between the receiving end and the wireless terminal.

With reference to the third possible implementation of the second aspect, in a fifth possible implementation manner of the second aspect, the N is greater than 1, the method further includes:

The receiving end receives the third packet from the sending end, where the third packet is a packet with a first identifier added to the fourth packet, where the first identifier is used to identify the fourth packet. The message is a message in the N packets, where the N packets are N packets before the data stream to which the second packet belongs, and the receiving end sends the message to the wireless terminal. Three messages. In the embodiment of the present invention, after receiving the first received packet carrying the first identifier, the receiving end does not copy the subsequently received packet carrying the first identifier, thereby reducing the receiving end and the wireless terminal. The link between the burden.

With reference to any one of the possible implementations of the second aspect to the fifth possible implementation of the second aspect, in the sixth possible implementation manner of the second aspect, the first identifier is carried in the a differentiated service code point DSCP field of the first packet; or the first identifier is carried in an option number field of the first packet.

In conjunction with the sixth possible implementation of the second aspect, in a seventh possible implementation of the second aspect, the first identifier may be an identifier on the 5th bit of the DSCP field.

In conjunction with the sixth possible implementation of the second aspect, in a seventh possible implementation of the second aspect, the first identifier may be a predetermined number in an option number field.

A third aspect of the embodiments of the present invention provides a sending apparatus, including:

An obtaining unit, configured to obtain a first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet The message is a message in the N packets, where the N packets are N packets before the data stream is transmitted, and N is greater than 0 and less than The number of packets of the data stream;

And a sending unit, configured to send the first packet to the receiving device.

In conjunction with the third aspect, in a first possible implementation manner of the third aspect, the obtaining unit is specifically configured to:

Determining, according to the second identifier carried in the second packet, that the second packet belongs to the N packets, where the second identifier is used to identify a location of the second packet in the data stream. ;

Adding the first identifier to the second packet to obtain the first packet.

A fourth aspect of the embodiments of the present invention provides a receiving apparatus, including:

a first receiving unit, configured to receive a first packet from the sending end, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet The message is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the packet of the data stream. Quantity

The processing unit is configured to process the first packet according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.

In conjunction with the fourth aspect, in a first possible implementation manner of the fourth aspect, the processing unit is specifically configured to:

After the received packet queue corresponding to the data flow exceeds the first threshold, the received packet that does not carry the first identifier is preferentially discarded.

With reference to the first possible implementation of the fourth aspect, in a second possible implementation manner of the fourth aspect, the processing unit is specifically configured to:

And obtaining, according to the first identifier and the corresponding relationship, the first parameter, where the correspondence includes the first identifier and the first parameter, where the first parameter includes a second threshold and a discard probability, and the discard probability Indicates the percentage of operations that perform packet discarding;

After the received packet queue corresponding to the data stream exceeds the second threshold, the received packet that does not carry the first identifier is discarded according to the discarding probability.

In conjunction with the fourth aspect, in a third possible implementation manner of the fourth aspect, the processing unit is specifically configured to:

Copying the first packet to obtain M first messages, where M is an integer greater than or equal to 2;

And transmitting the M first messages to a wireless terminal.

With reference to the third possible implementation manner of the fourth aspect, in a fourth possible implementation manner of the fourth aspect, the M is a value determined according to a default value of the number of copies of the message; or

The M is a value determined according to the number of accesses and/or the quality of the link between the receiving end and the wireless terminal, and the number of accesses is the number of wireless terminals that have accessed the receiving end.

In conjunction with the third possible implementation of the fourth aspect, in a fifth possible implementation manner of the fourth aspect, the device is greater than 1, the device further includes:

a second receiving unit, configured to receive a third packet from the sending end, where the third packet is a packet that adds a first identifier to the fourth packet, where the first identifier is used to identify the The fourth packet is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs.

And a sending unit, configured to send the third packet to the wireless terminal.

A fifth aspect of the embodiments of the present invention provides a transmitting end, including: a processor, a transmitter, and a communication bus; wherein the processor and the transmitter complete communication with each other through the communication bus;

The processor is used to:

Obtaining a first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N packets. In the message in the text, the N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets in the data stream;

The transmitter is used to:

Sending the first packet to the receiving end.

With reference to the fifth aspect, in a first possible implementation manner of the fifth aspect, the processor is specifically configured to:

Determining, according to the second identifier carried in the second packet, that the second packet belongs to the N packets The second identifier is used to identify a location of the second packet in the data stream;

Adding the first identifier to the second packet to obtain the first packet.

A sixth aspect of the embodiments of the present invention provides a receiving end, including: a processor, a receiver, a transmitter, and a communication bus; wherein the receiver, the transmitter, and the processor are completed by using the communication bus Communication with each other;

The receiver is used to:

Receiving a first packet from the sender, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N packets. In the message, the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the number of packets in the data stream; :

The first packet is processed according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.

In conjunction with the sixth aspect, in a first possible implementation manner of the sixth aspect, the processor is specifically configured to:

With reference to the first possible implementation manner of the sixth aspect, in a second possible implementation manner of the sixth aspect, the processor is specifically configured to:

In conjunction with the sixth aspect, in a third possible implementation manner of the sixth aspect, the processor is specifically configured to:

The transmitter is used to:

And transmitting the M first messages to a wireless terminal.

With reference to the third possible implementation manner of the sixth aspect, in a fourth possible implementation manner of the sixth aspect, the M is a value determined according to a default value of the number of copies of the message; or

With reference to the third possible implementation manner of the sixth aspect, in a fifth possible implementation manner of the sixth aspect, the N is greater than 1, the receiver is specifically configured to:

And the third packet is configured to receive the third packet from the sending end, where the third packet is a packet that is added with the first identifier in the fourth packet, where the first identifier is used to identify that the fourth packet is a message in the N packets, where the N packets are N packets before the data stream to which the second packet belongs;

The transmitter is specifically configured to:

Sending the third message to the wireless terminal.

One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

In the embodiment of the present invention, the sending end obtains the first packet in the data stream, and the first packet is the first packet, and the first packet is sent to the receiving end. The first packet is one of the N packets before the data stream is transmitted. After receiving the first packet, the receiving end processes the first packet according to the packet transmission policy. Processing the first packet to make the processing mode more flexible, and satisfying the requirement that the receiving end reduces the packet loss rate of the N packets before the data stream is completed, thereby reducing the data stream before the transmission is completed. The loss of N packets, that is, the timeout retransmission caused by the loss of the last packet of the data stream, shortens the task completion time.

DRAWINGS

Figure 1 is a schematic diagram of a data center;

2 is a schematic diagram of a metropolitan area network;

3 is a flowchart of a method for transmitting data by a transmitting device according to an embodiment of the present invention;

4 is a schematic diagram of timeout retransmission due to packet loss in an embodiment of the present invention;

FIG. 5 is a schematic diagram of a first implementation manner of setting a first identifier according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a second implementation manner of setting a first identifier according to an embodiment of the present disclosure;

7 is a flowchart of a method for transmitting data by a receiving device according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a transmission process of a packet carrying a first identifier in a data center according to an embodiment of the present disclosure;

FIG. 9 is a flowchart of a method for a receiving device to perform a second processing manner on a packet carrying a first identifier according to an embodiment of the present disclosure;

10 is a schematic diagram of a transmission process of a packet carrying a first identifier in a metropolitan area network according to an embodiment of the present invention;

FIG. 11 is a schematic diagram of functional modules of a sending apparatus according to an embodiment of the present invention; FIG.

12 is a schematic structural diagram of hardware of a transmitting end according to an embodiment of the present invention;

FIG. 13 is a schematic diagram of functional modules of a receiving apparatus according to an embodiment of the present invention; FIG.

FIG. 14 is a schematic structural diagram of hardware of a receiving end according to an embodiment of the present invention.

detailed description

The embodiment of the present invention provides a data transmission method, a sending device, and a receiving device, which are used to solve the problem in the prior art. When a lost packet occurs at the end of the TCP stream, a timeout retransmission may occur, which may result in Technical issues with extended mission completion time.

The term "and/or" in this context is merely an association describing the associated object, indicating that there may be three relationships, for example, A and / or B, which may indicate that A exists separately, and both A and B exist, respectively. B these three situations. In addition, the character "/" in this article generally indicates that the contextual object is an "or" relationship.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of a data center. The data center includes multiple servers, top of Rack (Tor) switches. The data center also includes core switches and aggregation switches. In a data center network, the Tor switch causes TCP incast due to many-to-one communication. problem. The TCP incast problem refers to the data center network. As the number of servers participating in data transmission increases, the generated data traffic will overflow the buffer of the Tor switch. Therefore, packet loss occurs at the Tor switch, and the policy used for packet loss is random discard. That is, N packets before the data stream is transmitted may be discarded by the Tor switch, resulting in timeout retransmission. .

Generally speaking, the core ports of the data center, the uplink ports of the aggregation switch and the Tor switch, such as the ports that the Tor switch communicates with the aggregation switch, do not cause congestion. If the congestion occurs, the solution provided in the embodiment of the present invention may also be used.

Please refer to FIG. 2, which is a schematic diagram of a metropolitan area network. In the network, some network devices limit traffic according to users, resulting in packet loss, such as Broadband Network Gateway (BNG). As the BNG will limit traffic according to the user, if the rate of receiving packets is far greater than the available bandwidth of the user, packet loss will occur at the BNG, and the policy used for packet loss is random discard, that is, the data stream is completed. N packets before transmission may be discarded by the BNG, resulting in timeout retransmission. In addition, for a Wireless Fidelity Access Point (WIFI AP) in a home network, such as a home gateway (HGW), an optical network terminal (ONT), and a cable modem (Cable Modem) , CM). The destination of the WIFI AP is the wireless terminal that accesses the network through the WIFI. The radio link feature may also cause more packet loss, which may result in the loss of N packets before the data stream is transmitted. The generation of the biography. The data transmission method provided by the embodiment of the present invention is described in detail below.

First, the method of transmitting data at the transmitting end will be described. In the embodiment of the present invention, the transmitting end may be the server 1 in FIG. 1; the receiving end may be the Tor switch in FIG. 1 or the BNG in FIG. 2 . As shown in Figure 3, the method includes the following:

The sending end obtains the first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet. For the packets in the N packets, the N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets in the data stream.

32. The sending end sends the first packet to a receiving end.

In the above, the sending end may determine, according to the second identifier carried in the second packet, that the second packet belongs to the N packets, and the second identifier is used to identify the second packet. The location of the text in the data stream. In the embodiment of the present invention, the second identifier may be a field serial number carried in the packet, and the field serial number is used to identify the location of the second packet in the data stream. For example, if the field number seq=92 carried in the message indicates that the first byte of the data part in the message is 92. The sender can determine, according to the value of the field number carried in the packet in the data stream, that the second packet belongs to the N packets before the data stream is transmitted. Then, the sending end adds a first identifier to the second packet to obtain the first packet.

In the above, the sending end inserts the received second packet into the queue to which it belongs according to the sequence of the received packets, and determines that the second packet belongs to the N according to the ranking of the queue. Messages. In this way, the transmitting end does not need to identify the second identifier of each received message and determine whether it is N packets, which helps to further reduce overhead and save time.

For a value of N, a possible case is that the specific value of N may be a preset value, and the value of N may be set to be any value greater than 0 and smaller than the number of packets of the data stream. Another possible case is that the specific value of N is set according to the number of triggering timeout retransmission confirmation characters (Acknowledgement, ack). For example, as shown in FIG. 4, when the data stream is sent to the receiving end by the transmitting end, when the field number seq=100 of the message in the middle of the data stream is lost, the subsequent message seq=120, seq=135 and seq= After the 141 transmission, the sender receives the three acks sent by the receiver as ack=100, and then triggers the sender to resend the message seq=100 by fast retransmission. That is to say, when the sender receives the three acks sent by the receiver, it will trigger the fast retransmission. In the case of the data stream, when the fourth packet of the last stream of the data stream is discarded, if the next three packets are discarded. If the transmission succeeds, the fast retransmission can be triggered. When the last three packets before the data stream is lost, no subsequent packets can trigger fast retransmission. Therefore, the value of N can be 3.

The following describes how the sender adds the first identifier to the second packet.

A possible implementation manner is: carrying the first identifier in a Differentiated Services Code Point (DSCP) field of the packet. As shown in Figure 5, the Internet Protocol version 4 (IPv4) packet is used as an example. The sender will be in the DSCP field. If the fifth bit is set to the identifier 1, the fifth bit of the DSCP field of the packet is the identifier 1, indicating that the packet is one of the N packets before the data stream is transmitted.

Specifically, in the defined packet in the DSCP field, the fifth bit of the Assured Forwarding (AF) hop-by-hop behavior (PHB) packet and the Expedited Forwarding (EF) PHB packet are all 0, as the code recommended by AF is shown in Table 1. Table 1 shows the three drop priorities for each class in the AF, along with the recommended DSCP associated with each priority. Each DSCP is represented by its AF value, decimal value, and binary value, respectively. In the method provided by the embodiment of the present invention, the fifth bit in the DSCP field sets the identifier 1 to indicate that the packet is one of the N packets before the data stream is completed.

Table 1

Another possible implementation manner is: carrying the first identifier in an option number field of the first packet. Taking an IPv4 packet as an example, the sender can set the option number field in the option of the packet header of the packet to a predetermined number. If the number of the message in the option number field is a predetermined number, it indicates that the message data stream completes one of the N messages before the transmission.

Specifically, as shown in Figure 6, the IPV4Options field is represented by one byte and contains three fields: a 1-bit copied flag, a 2-bit option class, and a 5-bit option number. . In order to identify the first message, one of the possible extensions is shown in FIG. 6. The predetermined number of the option number field is expressed as 27 in decimal notation and 11011 in binary.

It should be noted that the predetermined number used as the first identifier should be different from other currently defined numbers. For example, the number 27 is a number that is not defined, and the predetermined number can be defined as 27.

Next, a data transmission method of the receiving device is described. As shown in FIG. 7, the method includes:

71. The receiving end receives the first packet from the sending end, where the first packet is a packet that adds the first identifier to the second packet, where the first identifier is used to identify that the second packet is A packet of the N packets, the N packets being N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the number of packets of the data stream.

In the embodiment of the present invention, the transmitting end sends the first packet with the first identifier added to the data stream to the receiving end by performing the method shown in FIG. Therefore, the receiving end can receive the first packet in the data stream sent by the sending end.

72. The receiving end processes the first packet according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet. In the embodiment of the present invention, the following two possible processing manners in the message transmission policy are described.

In the first processing mode, the receiving end generates congestion or limits the flow of the user. When the packet needs to be discarded, the first identifier in the packet is identified, and the packet carrying the first identifier is preferentially discarded.

In the second processing mode, the first packet carrying the first identifier is copied and the plurality of the first packet is sent by identifying the first identifier in the WIFI AP in the home network.

First, the first processing method will be explained. In the first processing mode, the receiving end may be the Tor switch in FIG. 1 or the BNG in FIG. 2. The method includes: after receiving the received packet queue of the data stream, the receiving end preferentially discards the received packet that does not carry the first identifier.

The first threshold is the number of packets in the packet queue before the receiver is ready to discard the packet. When the length of the packet queue corresponding to the data stream that is buffered in the receiving end reaches the first threshold, the receiving end starts discarding the packet. The first threshold may be a length of a preset message queue.

A possible implementation manner is as follows: the receiving end determines whether the packet is a packet to be discarded according to the discarding probability; wherein the discarding probability is a percentage of the operation of discarding the packet. In the embodiment of the present invention, the size of the discard probability is proportional to the length of the packet queue; if the packet to be discarded is the first packet carrying the first identifier, the first packet is not discarded; If the packet to be discarded is not If the first identifier is carried, the packet is discarded.

In the actual application, the random early drop (RED) algorithm can be used to determine whether the packet is a packet to be discarded, or other algorithms can be used. The RED algorithm is used as an example. When the packet queue buffered at the receiving end reaches the first threshold, the packet discarding probability is randomly determined by the discarding probability. As the queue length increases, the probability of packet discarding increases. . And, when the packet is determined to be a packet to be discarded by the RED algorithm, if the packet to be discarded does not carry the first identifier, the packet is discarded; if the packet to be discarded carries the first identifier, the packet is not discarded. The message.

Another possible implementation manner is: the receiving end obtains a first parameter according to the first identifier and the corresponding relationship, where the corresponding relationship includes the first identifier and the first parameter, and the first parameter The second threshold and the discarding probability are used, and the discarding probability is used to indicate the percentage of the operation of discarding the message; the receiving end, after the received packet queue corresponding to the data stream exceeds the second threshold, according to the The discarding probability discards the received packet carrying the first identifier. The second threshold is a length of a preset queue, such as a minimum threshold of a queue length. The second threshold may be the same as the first threshold or may be different from the first threshold.

The first identifier is an identifier of a DSCP field that is set in the first packet, and the first parameter is a packet discarding parameter corresponding to the first identifier, where the first parameter includes a second threshold and a discard probability, and the second threshold The number of packets in the packet queue before the packet is discarded. The discarding probability is used to indicate the percentage of the packet discarding operation.

In the actual application, the weighted random early detection (WRED) algorithm can be used to discard the packet carrying the first identifier. When the packet needs to be discarded, the WRED algorithm is used according to the quality of service (Quality of Service, QoS) priority classifies messages into corresponding categories. Each category corresponds to a discarding policy. Each discarding policy has its own packet discarding parameters, including: a second threshold and a discarding probability. The receiving end discards the packets of the class according to the packet discarding parameters corresponding to each category.

In the embodiment of the present invention, when the WRED algorithm is used to classify the packet, the DSCP field may be mapped to the QoS priority of the first packet by setting the identifier 1 in the fifth bit of the DSCP field of the first packet. In a data stream, the QoS priority of the packet carrying the first identifier is lower than that of the non-portable packet. The QoS priority of an identified message is one level higher. For example, in a data stream, the DSCP field of the packet carrying the first identifier is "001100", and the DSCP field of the packet carrying the first identifier is "001101", and the packet carrying the first identifier is carried. The QoS priority is one level higher than the QoS priority of the message that does not carry the first identifier. Moreover, the packet with a higher priority corresponds to a higher second threshold and a lower discarding probability than the packet with a lower priority. Therefore, it is possible to preferentially discard packets that do not carry the first identifier.

The following is an example to illustrate the transmission process of the message carrying the first identifier in the data center. Please refer to Figure 8, including the following:

81. The server 1 sets a first identifier in the N packets before the data stream sent to the Tor switch completes the transmission, and sends the N packets to the Tor switch.

After receiving the packet in the data stream, the Tor switch identifies the packet carrying the first identifier, and discards the packet that does not carry the first identifier when the packet is discarded by the Tor switch.

83. The Tor switch sends the packet carrying the first identifier to the server 2.

Next, the second processing method will be described. As shown in Figure 9, the second processing method includes:

91. The receiving end copies the first packet, and obtains the M first packets, where the M is an integer greater than or equal to 2.

92. The receiving end sends the M first messages to a wireless terminal.

In the second processing mode, the receiving end is a WIFI AP, such as the home gateway HGW in FIG. 2, the optical network terminal ONT, and the cable modem CM. In practical applications, the receiving end may also be another network device with a built-in WIFI AP.

In the second processing mode, when the wireless terminal accesses the network by using the WIFI interface, the packet loss rate of the first packet is reduced in the transmission of the WIF interface. Rate, after the WIFI AP identifies the first packet carrying the first identifier, the first packet is copied, and the first packet is lost by sending the M first packet. rate.

In the embodiment of the present application, a possible implementation manner is: if a data stream includes multiple packets carrying the first identifier, the receiving end may copy each packet carrying the first identifier to reduce Packet loss rate.

In the embodiment of the present application, the M may be a value determined according to a default value of the number of copies of the message. The M may also be a value determined according to the number of accesses and/or the quality of the link between the receiving end and the wireless terminal, where the number of accesses is the number of wireless terminals that have accessed the receiving end.

Specifically, the M value may be inversely proportional to the link quality, and is proportional to the number of wireless terminals, that is, the better the link quality, the smaller the M value, the larger the number of wireless terminals, and the larger the M value. In practical applications, the M value may also be other functional relationships related to multiple factors such as link quality and number of wireless terminals.

Another possible implementation manner is that the receiving end can copy the first packet carrying the first identifier in the received one of the data streams, and carries the carried in the subsequently received data stream. The first identified packet is not copied to reduce the number of packets that need to be sent by the receiving end, thereby reducing the link load between the receiving end and the wireless terminal.

Then, after the method, the method further includes: receiving, by the receiving end, a third packet from the sending end, where the third packet is a packet that adds a first identifier to the fourth packet, where the An identifier is used to identify that the fourth packet is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs, and the receiving is performed; Sending, by the terminal, the third packet to the wireless terminal. That is, after the receiving end copies the first packet carrying the first identifier, the receiving end does not copy the subsequently received third packet carrying the first identifier.

According to the TCP protocol, when the receiving end receives three acks sent by the wireless terminal, the receiving end will trigger the receiving end to resend the lost message by fast retransmission. If there is a lost packet before the first packet, the M is successfully sent the first packet and the M first packet obtained by the replication to the M. The wireless terminal receives the ack corresponding to the first packet and the M acks corresponding to the M first messages, and triggers the receiving end to resend the lost packet by fast retransmission, thereby avoiding The generation of timeout retransmissions, at the same time, reduces the link load between the receiving end and the wireless terminal.

In the embodiment of the present invention, when receiving the first message, the receiving end WIFI AP may send the copied M first message after sending the first message, or may pass the timing according to a certain algorithm. The device delays transmitting the M first messages in a certain time.

It should be noted that the destination of the packet sent by the WIFI AP in the embodiment of the present invention is The wireless terminal transmitted through the WIF interface can improve the transmission reliability of the first packet, reduce the packet loss rate, and not consume the bandwidth of other network devices by transmitting the M first packets.

The following is an example to illustrate the transmission process of a packet carrying the first identifier in the metropolitan area network. Please refer to FIG. 10, including the following contents:

101. The server 1 sets a first identifier in each of the N packets before the data stream sent to the wireless terminal completes transmission, and sends the N packets to the BNG.

102. After receiving the packet in the data stream, the BNG identifies the packet carrying the first identifier. When the BNG needs to discard the packet, the BNG preferentially discards the packet that does not carry the first identifier.

103. The BNG sends the packet carrying the first identifier to the WIFI AP.

After receiving the packet in the data stream, the WIFI AP identifies the packet carrying the first identifier and copies the packet carrying the first identifier.

105. The WIFI AP sends the packet and the copy message of the packet to the wireless terminal.

Based on the same inventive concept, an embodiment of the present invention further provides a sending apparatus, as shown in FIG.

The obtaining unit 111 is configured to obtain a first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet. The message is a packet of the N packets, where the N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets of the data stream;

The sending unit 112 is configured to send the first packet to the receiving device.

Optionally, the obtaining unit 111 is specifically configured to:

Adding the first identifier to the second packet to obtain the first packet.

The various changes and specific examples in the method for transmitting data in the foregoing embodiment of FIG. 3 are also applicable to the transmitting apparatus of this embodiment. Through the foregoing detailed description of the method for data transmission, those skilled in the art can clearly know this. The implementation method of the transmitting device in the embodiment is not detailed here for the sake of brevity of the description.

Based on the same inventive concept, an embodiment of the present invention further provides a receiving end, as shown in FIG. 12, including: a processor 602, a transmitter 601, and a communication bus 600; wherein the processor 602 and the transmitter 601 pass The communication bus 600 completes communication with each other;

The processor 602 is configured to:

The transmitter 601 is configured to:

Sending the first packet to the receiving end.

Optionally, the processor 602 is specifically configured to:

Adding the first identifier to the second packet to obtain the first packet.

Further, in FIG. 12, communication bus 600 can include any number of interconnected buses and bridges, and communication bus 600 connects various circuits including one or more processors represented by processor 602 and memory represented by memory 604. together. Communication bus 600 may also couple various other circuits, such as peripherals, voltage regulators, and power management circuits, as is known in the art and, therefore, will not be further described herein. Bus interface 605 provides an interface between communication bus 600 and transmitter 601. Transmitter 601 can be a transceiver that provides means for communicating with various other devices on a transmission medium.

Processor 602 is responsible for managing communication bus 600 and general processing, while memory 604 can be used to store data used by processor 602 in performing operations.

The various changes and specific examples in the foregoing method for transmitting data in the embodiment of FIG. 3 are also applicable to the transmitting end of the present embodiment. Those skilled in the art can clearly know the present disclosure through the foregoing detailed description of the method for data transmission. The implementation method of the transmitting end in the embodiment, so for the sake of brevity of the description, it will not be described in detail herein.

Based on the same inventive concept, an embodiment of the present invention further provides a receiving device, as shown in FIG. 13, including:

The first receiving unit 131 is configured to receive a first packet from the sending end, where the first packet is a packet that adds a first identifier to the second packet, where the first identifier is used to identify the first packet. The second packet is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the data stream. Number of texts;

The processing unit 132 is configured to process the first packet according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.

Optionally, the processing unit 132 is specifically configured to:

And transmitting the M first messages to a wireless terminal.

Optionally, the M is a value determined according to a default value of the number of copies of the message; or

Optionally, the N is greater than 1, and the device further includes:

a second receiving unit, configured to receive a third packet from the sending end, where the third packet is a packet that adds a first identifier to the fourth packet, where the first identifier is used to identify the Fourth message For the packets in the N packets, the N packets are N packets before the data stream to which the second packet belongs.

The various changes and specific examples in the method for transmitting data in the foregoing embodiment of FIG. 7 are also applicable to the receiving apparatus of the present embodiment. Those skilled in the art can clearly know the present by the foregoing detailed description of the method for data transmission. The implementation method of the receiving device in the embodiment is not detailed here for the sake of brevity of the description.

Based on the same inventive concept, an embodiment of the present invention further provides a receiving end, as shown in FIG. 14, comprising: a processor 702, a receiver 701, a transmitter 703, and a communication bus 700; wherein the receiver 701, the The transmitter 703 and the processor 702 complete communication with each other through the communication bus 700;

The receiver 701 is configured to:

Receiving a first packet from the sender, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N packets. In the message, the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the number of packets in the data stream;

The processor 702 is configured to:

Optionally, the processor 702 is specifically configured to:

After the received message queue corresponding to the data flow exceeds the second threshold, according to the The discarding probability discards the received packet that does not carry the first identifier.

Optionally, the processor 702 is specifically configured to:

The transmitter 703 is configured to:

And transmitting the M first messages to a wireless terminal.

Optionally, the N is greater than 1, and the receiver 701 is specifically configured to:

The transmitter 703 is specifically configured to:

Sending the third message to the wireless terminal.

Further, in FIG. 14, communication bus 700 can include any number of interconnected buses and bridges, and communication bus 700 connects various circuits including one or more processors represented by processor 702 and memory represented by memory 704. together. Communication bus 700 may also couple various other circuits, such as peripherals, voltage regulators, and power management circuits, as is known in the art and, therefore, will not be further described herein. Bus interface 705 provides an interface between communication bus 700 and transmitter 703. Receiver 701 and transmitter 703 may be the same component, i.e., a transceiver, providing means for communicating with various other devices on a transmission medium.

Processor 702 is responsible for managing communication bus 700 and general processing, while memory 704 can be used to store data used by processor 702 in performing operations.

The various changes and specific examples in the foregoing method for transmitting data in the embodiment of FIG. 7 are also applicable to the receiving end of the embodiment. The foregoing detailed description of the method for data transmission can be clearly known to those skilled in the art. The implementation method of the receiving end in the embodiment, so for the specification Concise, no longer detailed here.

Those skilled in the art will appreciate that embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (system), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing device to produce a machine for the execution of instructions for execution by a processor of a computer or other programmable data processing device. Means for implementing the functions specified in one or more of the flow or in a block or blocks of the flow chart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.

Finally, it should be noted that the above embodiments are only used to exemplify the technical solutions of the present invention, and are not limited thereto; although the beneficial effects brought by the present invention and the present invention are described in detail with reference to the foregoing embodiments, the field It should be understood by those skilled in the art that the technical solutions described in the foregoing embodiments may be modified or equivalently replaced with some of the technical features; and such modifications or substitutions do not deviate from the essence of the corresponding technical solutions. The scope of the claims.

Claims

A data transmission method, characterized in that the method comprises:

The sending end obtains the first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N. The message in the packet, the N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets in the data stream;

The sending end sends the first packet to the receiving end.
The method according to claim 1, wherein the obtaining, by the transmitting end, the first message in the data stream comprises:

The sending end determines, according to the second identifier carried in the second packet, that the second packet belongs to the N packets, and the second identifier is used to identify the second packet in the data. The position in the stream;

The sending end adds the first identifier to the second packet, and obtains the first packet.
The method according to claim 1 or 2, wherein the first identifier is carried in a differentiated service code point DSCP field of the first packet; or

The first identifier is carried in an option number field of the first packet.
A data transmission method, characterized in that the method comprises:

The receiving end receives the first packet from the sending end, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify that the second packet is N a packet in the packet, where the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the number of packets in the data stream;

The receiving end processes the first packet according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.
The method according to claim 4, wherein the processing of the first packet by the receiving end according to the packet transmission policy comprises:

The receiving end preferentially discards the received packet that does not carry the first identifier after the received packet queue corresponding to the data stream exceeds the first threshold.
The method of claim 5, wherein the receiving end preferentially discarding the received message that does not carry the first identifier comprises:

The receiving end obtains a first parameter according to the first identifier and the corresponding relationship, where the corresponding relationship includes the first identifier and the first parameter, where the first parameter includes a second threshold and a discarding probability, where The drop probability is used to indicate the percentage of operations that perform packet discarding;

The receiving end discards the received packet carrying the first identifier according to the discarding probability, after the received packet queue corresponding to the data stream exceeds the second threshold.
The method according to claim 4, wherein the processing of the first packet by the receiving end according to the packet transmission policy comprises:

The receiving end copies the first packet, and obtains the M first packets, where the M is an integer greater than or equal to 2;

The receiving end sends the M first messages to a wireless terminal.
The method of claim 7 wherein said M is a value determined based on a default value of the number of copies of the message; or

The M is a value determined according to the number of accesses and/or the quality of the link between the receiving end and the wireless terminal, and the number of accesses is the number of wireless terminals that have accessed the receiving end.
The method of claim 7, wherein the N is greater than 1, the method further comprising:

The receiving end receives the third packet from the sending end, where the third packet is a packet with a first identifier added to the fourth packet, where the first identifier is used to identify the fourth packet. The message is a message in the N packets, and the N packets are N packets before the data stream to which the second packet belongs.

The receiving end sends the third packet to the wireless terminal.
The method according to any one of claims 4 to 9, wherein the first identifier is carried in a differentiated service code point DSCP field of the first packet; or

The first identifier is carried in an option number field of the first packet.
A transmitting device, characterized in that the transmitting device comprises:

An obtaining unit, configured to obtain a first packet in the data stream, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet The message is a message in the N packets, where the N packets are N packets before the data stream is transmitted, and N is greater than 0 and smaller than the number of packets in the data stream;

And a sending unit, configured to send the first packet to the receiving device.
The transmitting device according to claim 11, wherein the obtaining unit is specifically configured to:

Determining, according to the second identifier carried in the second packet, that the second packet belongs to the N packets, where the second identifier is used to identify a location of the second packet in the data stream. ;

Adding the first identifier to the second packet to obtain the first packet.
A receiving device, characterized in that the receiving device comprises:

a first receiving unit, configured to receive a first packet from the sending end, where the first packet is a packet with a first identifier added to the second packet, and the first identifier is used to identify the second packet The message is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs, and N is greater than 0 and smaller than the packet of the data stream. Quantity

The processing unit is configured to process the first packet according to a packet transmission policy, where the packet transmission policy includes a processing manner adopted by the first packet.
The receiving device according to claim 13, wherein the processing unit is specifically configured to:

After the received packet queue corresponding to the data flow exceeds the first threshold, the received packet that does not carry the first identifier is preferentially discarded.
The receiving device according to claim 14, wherein the processing unit is specifically configured to:

And obtaining, according to the first identifier and the corresponding relationship, the first parameter, where the correspondence includes the first identifier and the first parameter, where the first parameter includes a second threshold and a discard probability, and the discard probability Indicates the percentage of operations that perform packet discarding;

After the received message queue corresponding to the data flow exceeds the second threshold, according to the The discarding probability discards the received packet that does not carry the first identifier.
The receiving device according to claim 13, wherein the processing unit is specifically configured to:

Copying the first packet to obtain M first messages, where M is an integer greater than or equal to 2;

And transmitting the M first messages to a wireless terminal.
The receiving apparatus according to claim 16, wherein said M is a value determined based on a default value of the number of copies of the message; or

The M is a value determined according to the number of accesses and/or the quality of the link between the receiving end and the wireless terminal, and the number of accesses is the number of wireless terminals that have accessed the receiving end.
The receiving device according to claim 16, wherein the N is greater than 1, the device further comprising:

a second receiving unit, configured to receive a third packet from the sending end, where the third packet is a packet that adds a first identifier to the fourth packet, where the first identifier is used to identify the The fourth packet is a packet of the N packets, and the N packets are N packets before the data stream to which the second packet belongs.

And a sending unit, configured to send the third packet to the wireless terminal.