WO2022247307A1

WO2022247307A1 - Message transmission method and apparatus

Info

Publication number: WO2022247307A1
Application number: PCT/CN2022/071659
Authority: WO
Inventors: 郑述乾; 王伟; 姚笛
Original assignee: 华为技术有限公司
Priority date: 2021-05-28
Filing date: 2022-01-12
Publication date: 2022-12-01
Also published as: CN115412508A

Abstract

The present application relates to the field of communications. Disclosed are a message transmission method and apparatus, by means of which messages can be sorted. The method and apparatus are simply implemented and have high reliability. In the method, after receiving, from a sending end, a first message of a first service by means of a first path, a receiving end may determine a first delay parameter according to a first maximum transmission delay of a plurality of paths, obtain a first estimated reading time according to the first delay parameter, and a first sending time stamp that is carried in the first message, and read data of the first message according to the first estimated reading time.

Description

Method and device for transmitting messages

This application claims priority to a Chinese patent application filed with the State Intellectual Property Office of China on May 28, 2021, with application number 202110593746.8 and titled "Method and device for transmitting messages", the entire contents of which are hereby incorporated by reference Applying.

technical field

The present application relates to the communication field, in particular to a method and device for transmitting messages.

Background technique

As the demand for network bandwidth continues to grow, the scale of the network expands dramatically. However, in the network, the distribution of service data flow in time and space is uneven, which leads to unreasonable distribution of available bandwidth in time and space, low network bearing efficiency and data transmission efficiency, and long data transmission delay. big. For example, in FIG. 1A, data flow A of an edge node (provider edge, PE) 0 can be sent to PE 3 through a label switched path (label switched path, LSP) 101. Data flow B of PE 1 can be sent to PE 3 through LSP 102. Data flow C of PE 2 can be sent to PE 3 through LSP 103, LSP 104 or LSP 105. When data flow A is sent to PE 3 through LSP 101, data flow B is sent to PE 3 through LSP 102, and data flow C is sent to PE 3 through LSP 103, the load of congestion point A will be too high, and the network carrying efficiency And data transmission efficiency is reduced, and data transmission delay is increased. For another example, in FIG. 1B, if the network load is not high, the data flow D of PE 4 can be sent to PE 5 through LSP 106, LSP 107 or LSP 108. If the network load is too high to support the sending of the data stream D, the data stream D may not be sent until the network load decreases. For example, if the bandwidth required by the current data flow D is 6G, and the current available bandwidth of LSP 106 is 2G, the available bandwidth of LSP 107 is 3G, and the available bandwidth of LSP 108 is 1G, then LSP 106, LSP 107 and LSP 108 cannot The bandwidth requirement of data flow D is met, so data flow D cannot be sent until the available bandwidth of at least one LSP among LSP 106, LSP 107, and LSP 108 is greater than or equal to 6G. In this way, the network bearing efficiency and data transmission efficiency will be reduced, and the data transmission delay will be increased.

In order to improve network bearer efficiency and network transmission efficiency, and reduce data transmission delay, a multipath transmission technology is proposed. Through the multi-path transmission technology, multiple packets including the data of the data stream can be sent from the sending end to the receiving end through multiple paths. For example, in FIG. 1A, multiple packets including the data of data flow C can be sent to PE 3 through multiple paths in LSP 103, LSP 104 and LSP 105, so as to reduce the load of choke point A. For another example, in Fig. 1B, LSP 106, LSP 107 and LSP 108 can meet the bandwidth requirement of data flow D together, so multiple messages including the data of data flow D can be sent through LSP 106, LSP 107 and LSP 108 to PE 5. In this way, the data flow D does not need to wait for the network load to decrease before sending it.

It can be seen from the above description that the multi-path transmission technology can improve network bearing efficiency and network transmission efficiency, and reduce data transmission delay. However, multi-path transmission technology also brings new problems: the transmission delays of different paths are different, so the order in which the receiving end receives packets is different from the order in which the sending end sends packets, that is, the packets received by the receiving end are random. sequential. Therefore, after receiving the packets, the receiving end needs to sort the packets to restore the data flow. However, the current packet sorting methods either require relatively large computing resources and storage resources, and are relatively complicated to implement, or have high requirements on the network and low reliability.

Contents of the invention

The application provides a method and device for transmitting messages, which can sort the messages, and is simple to implement and highly reliable.

In order to achieve the above object, the embodiments of the present application adopt the following technical solutions:

In the first aspect, a method for transmitting a message is provided, and the communication device executing the method may be a receiving end; it may also be a module applied to the receiving end, such as a chip or a chip system. The following takes the execution subject as the receiving end as an example for description. The method includes: receiving a first packet of a first service sent by a sending end through a first path, the first packet carrying a first sending timestamp, the first sending timestamp corresponding to the time domain of the sending end, The time when the first message is sent, the first path is one of the multiple paths for transmitting the message of the first service to the receiving end; the first delay parameter of the first service is obtained, and the first delay The parameter is determined according to the first maximum transmission delay of the plurality of paths; the first estimated read time is obtained according to the first sending timestamp and the first delay parameter; the read time is read according to the first expected read time The data of the first message.

Based on the method provided in the first aspect above, the receiving end can sort the received messages as a whole without distinguishing services, which can reduce the complexity of the receiving end and reduce the consumption of computing resources and storage resources. Moreover, for any service, its packets are also in order, which does not affect the function of the service. In the process of sorting, the receiving end reads the data of the message according to the expected time to read the data of the message. The abnormal time stamp of a certain service does not affect the receiving end to read the data of other service messages, and the reliability is high. . The method provided in the first aspect above does not need to introduce aging time, and can reduce delay jitter. In addition, the method provided in the first aspect above has no special requirements on the transmission network, and can be deployed at the sending end and the receiving end, which is easy to implement.

With reference to the first aspect, in a possible implementation manner, reading the data of the first message according to the first expected reading time includes: in multiple queues sorted by time, according to the first expected reading time Enqueue the first message at the fetch time; when the first expected read time has been reached or exceeded, and the plurality of queues indicate that it is time to read the data of the first message, read the first The data of the message. Based on the above method, because the multiple queues are sorted according to time, after the first message is enqueued according to the first expected reading time, the receiving end realizes the sorting of the received messages. Subsequently, when the receiving end has reached or exceeded the first expected reading time and the multiple queues indicate that it is the turn to read the data of the first message, the receiving end reads the data of the first message, which can realize Read the data in the message according to the order of the message.

With reference to the first aspect, in a possible implementation manner, the multiple queues include a first queue, and enqueuing the first message according to the first expected read time includes: according to the first expected read time The difference between the current time and the information of the first message is input into the first queue, and the difference between the first expected reading time and the current time belongs to the time difference interval corresponding to the first queue. Based on the above method, the receiving end can put the first message into the queue according to the difference between the first expected reading time and the current time, that is, sorting of the received messages is realized.

In combination with the first aspect, in a possible implementation, if the first queue also stores information about the second message, if the first expected read time is earlier than the expected read time of the second message , then the time when the information of the first message is output from the first queue is earlier than the time when the information of the second message is output from the first queue; or, if the first expected reading time is later than the first As for the expected reading time of the second message, the time when the information of the first message is output from the first queue is later than the time when the information of the second message is output from the first queue. Based on the above method, the receiving end can determine the positions of the first message and the second message in the first queue according to the first expected reading time and the expected reading time of the second message, so as to realize the Document sorting.

With reference to the first aspect, in a possible implementation manner, the second message is other messages of the first service sent by the sending end except the first message, and the messages of other services sent by the sending end message, or other messages sent by the sender. Based on the above method, the receiving end can sort the received messages as a whole, without distinguishing between services and sending ends, which can reduce the complexity of the receiving end and reduce the consumption of computing resources and storage resources.

With reference to the first aspect, in a possible implementation manner, the method further includes: if the difference between the first expected read time and the current time is smaller than the minimum value of the time difference interval corresponding to the first queue, then The information of the first message is output from the first queue and input to the second queue, the second queue is included in the plurality of queues, and the difference between the first expected reading time and the current time belongs to the second queue The time difference interval corresponding to the queue. Based on the above method, multiple queues are connected in series in the time domain. Over time, information in the queues can be output from one queue and input to another. In this way, the receiving end can read the data of the message according to the sequence in the queue.

With reference to the first aspect, in a possible implementation manner, the multiple queues are divided into multiple groups, the first queue is included in the first group of queues, the second queue is included in the second group of queues, the The length of the time difference interval corresponding to the queues in the first group of queues is greater than the length of the time difference interval corresponding to the queues in the second group of queues. Based on the above method, different time difference interval lengths can be configured for queues of different groups. In this way, the number of queues can be greatly reduced, and the complexity of maintaining queues at the receiving end can be reduced.

With reference to the first aspect, in a possible implementation manner, obtaining the first expected read time according to the first sending time stamp and the first delay parameter includes: mapping the first sending time stamp to the receiving end In the time domain, the second sending time stamp is obtained; and the first expected reading time is obtained according to the second sending time stamp and the first delay parameter. Based on the above method, when the receiving end and the sending end are not synchronized in the time domain, the receiving end can perform time domain mapping between the sending end and the receiving end to unify the time domains of the receiving end and the sending end, and then The first estimated reading time is obtained in the unified time domain.

With reference to the first aspect, in a possible implementation manner, the method further includes: acquiring a first reference time stamp, a second reference time stamp, and a first clock mapping parameter, where the first reference time stamp is a time stamp at the sending end domain, the time corresponding to the first moment, the second reference timestamp is the time corresponding to the first moment in the time domain of the receiving end; the first sending timestamp is mapped to the time domain of the receiving end to obtain The second sending time stamp includes: obtaining the second sending time stamp according to the first sending time stamp, the first reference time stamp, the second reference time stamp and the first clock mapping parameter. Based on the above method, the second sending time stamp can be obtained, so that the first expected reading time can be obtained according to the second sending time stamp and the first delay parameter.

With reference to the first aspect, in a possible implementation manner, the first moment corresponds to the time when the sending end sends the third packet of the first service to the receiving end through the first path, and the method further includes: according to The first transmission delay, the second transmission delay and the adjustment factor adjust the first clock mapping parameter, the first transmission delay is the transmission delay of the first message from the sending end to the receiving end, the second The second transmission delay is the transmission delay of the third packet from the sending end to the receiving end. Based on the above method, the first clock mapping parameter can be adjusted, so that the time domain mapping between the sending end and the receiving end is more accurate.

With reference to the first aspect, in a possible implementation manner, the first delay parameter is determined according to the first maximum transmission delay of the multiple paths, including: the first delay parameter is determined according to the first maximum transmission delay of the multiple paths Determined by the first maximum transmission delay and the first margin, the first margin is a positive number. Based on the above method, a compensation value, that is, the first margin, is used to make the first maximum transmission delay compensated according to the compensation value (ie, the first delay parameter) greater than or equal to the maximum transmission delays of multiple paths. In this way, it is possible to avoid the situation that the estimation of the maximum transmission delay of multiple paths is small, which leads to wrong ordering of packets.

With reference to the first aspect, in a possible implementation manner, if the difference between the first delay parameter and the first maximum transmission delay is greater than a first threshold and lasts for a first time, then adjust the first delay parameter. Based on the above method, if the difference between the first delay parameter and the first maximum transmission delay is greater than the first threshold and lasts for the first time, it may indicate that the current first delay parameter is too large. In this case, the receiving end may adjust the first time delay parameter to avoid unnecessary time delay introduced due to a large first time delay.

With reference to the first aspect, in a possible implementation manner, the method further includes: comparing the stored fourth sending timestamp with the size of the first sending timestamp, where the fourth sending timestamp is carried in the fifth packet Herein, the fifth message is the latest message of the first service that was read before the first message; if the fourth sending time stamp is greater than the first sending time stamp, the fourth sending time stamp is adjusted A delay parameter. Based on the above method, if the fourth sending timestamp is greater than the first sending timestamp, it means that the first packet is wrongly sorted. In this case, it means that the current first delay parameter is too small, and therefore the first delay parameter may be adjusted to make the first delay parameter more accurate.

With reference to the first aspect, in a possible implementation manner, the method further includes: receiving a fourth message of the first service sent by the sending end, where the fourth message carries a third sending timestamp, and the third The sending time stamp corresponds to the time when the fourth message is sent in the time domain of the sending end; comparing the size of the first sending time stamp and the third sending time stamp to determine whether the ordering of the first message is correct; If the first packet is wrongly sorted, adjust the first delay parameter. Based on the above method, in the case that the first packet sorting error is detected, it can be determined that the current first delay parameter is too small, so the first delay parameter can be adjusted to make the first delay parameter more accurate.

With reference to the first aspect, in a possible implementation manner, the method further includes: if the sequence of the first packet is wrong, sending an alarm message. Based on the above method, the receiving end can send the alarm information, so that the user or the administrator can perform further processing according to the alarm information.

In a second aspect, a communication device for implementing the above method is provided. The communication device may be the receiving end in the above first aspect, or a device including the above receiving end. The communication device includes a corresponding module, unit, or means (means) for implementing the above method, and the module, unit, or means may be implemented by hardware, software, or by executing corresponding software on hardware. The hardware or software includes one or more modules or units corresponding to the above functions.

With reference to the second aspect above, in a possible implementation manner, the communication device may include a receiving module and a processing module. The receiving module, which may also be referred to as a receiving unit, is configured to implement the receiving function in the above first aspect and any possible implementation manner thereof. The receiving module may be composed of a transceiver circuit, a transceiver, a transceiver or a communication interface. The processing module may be used to implement the processing function in the above first aspect and any possible implementation manner thereof. The processing module may be, for example, a processor.

In a third aspect, a communication device is provided, including: a processor; the processor is configured to be coupled with a memory, and after reading an instruction in the memory, execute the above-mentioned first aspect and any possible implementation thereof according to the instruction method described in . The communication device may be the receiving end in the above first aspect and any possible implementation manner thereof, or a device including the above receiving end.

With reference to the third aspect above, in a possible implementation manner, the communications device further includes a memory, where the memory is configured to store necessary program instructions and data.

With reference to the third aspect above, in a possible implementation manner, the communication device is a chip or a chip system. Optionally, when the communication device is a system-on-a-chip, it may consist of chips, or may include chips and other discrete devices.

In a fourth aspect, a communication device is provided, including: a processor and an interface circuit; the interface circuit is used to receive computer programs or instructions and transmit them to the processor; the processor is used to execute the computer programs or instructions, so that the communication The device executes the method described in the above first aspect and any possible implementation manner thereof.

With reference to the fourth aspect above, in a possible implementation manner, the communication device is a chip or a chip system. Optionally, when the communication device is a system-on-a-chip, it may consist of chips, or may include chips and other discrete devices.

In a fifth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores instructions, and when it is run on a computer, the computer can execute the above-mentioned first aspect and any possible implementation manners thereof. the method described.

In a sixth aspect, a computer program product including instructions is provided, and when it is run on a computer, the computer can execute the method described in the above first aspect and any possible implementation thereof.

In a seventh aspect, a method for transmitting a message is provided, the method comprising: inserting a first sending timestamp into a first message of a first service at a sending end; sending the first message to a receiving end through a first path text, wherein the first sending timestamp corresponds to the time domain of the sending end; the time of sending the first message, and the first path is one of the multiple paths for transmitting the message of the first service to the receiving end One: The receiving end executes the method described in the above first aspect and any possible implementation thereof.

According to an eighth aspect, a communication system is provided, and the communication system includes: a sending end and a receiving end; the sending end is configured to insert a first sending time stamp into a first packet of a first service through a first path sending the first message to the receiving end, the first sending time stamp corresponds to the time when the first message is sent in the time domain of the sending end, and the first path is to transmit the message of the first service to the One of the multiple paths of the receiving end; the receiving end is configured to execute the method described in the above first aspect and any possible implementation manner thereof.

Wherein, for the technical effects brought about by any one of the possible implementations from the second aspect to the eighth aspect, please refer to the technical effects brought about by the above-mentioned first aspect and any possible implementations thereof, and will not be repeated here. .

Description of drawings

FIG. 1A is a first schematic diagram of a network transmission path;

FIG. 1B is a second schematic diagram of a network transmission path;

FIG. 2A is a schematic diagram of a network transmission path provided by an embodiment of the present application;

FIG. 2B is a schematic diagram of sorting messages according to timestamps provided by the embodiment of the present application;

FIG. 3 is a schematic diagram of message transmission provided by an embodiment of the present application;

FIG. 4 is a schematic diagram of a communication system architecture provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a hardware structure of a communication device provided by an embodiment of the present application;

FIG. 6 is a schematic flowchart of a method for transmitting a message provided in an embodiment of the present application;

FIG. 7A is a first schematic diagram of multiple queues provided by the embodiment of the present application;

FIG. 7B is a second schematic diagram of multiple queues provided by the embodiment of the present application;

FIG. 8 is a schematic diagram of receiving a message at a receiving end provided in an embodiment of the present application;

FIG. 9 is a schematic structural diagram of a communication device provided by an embodiment of the present application.

Detailed ways

The implementation of the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

In order to solve the problem that the packets received by the receiving end are out of order caused by multi-path transmission, the sending end can send packets to the receiving end through various methods, so that the receiving end can sort the received packets to restore data flow. For example, the sender can send a message to the receiver in the following ways:

Method 1: The sender can insert a sequence number (SN) into the message sent to the receiver. The SN is granular by service, that is to say, each service corresponds to a group of SNs. For any service, SN increases gradually with the increase of the number of packets sent. For example, for any service, the SN inserted in the first message sent by the sender is 1, the SN inserted in the second message is 2, the SN inserted in the third message is 3, and so on. These messages can be sent to the receiver through multiple transmission paths. After receiving these packets, the receiving end can sort the packets according to the SN. Exemplarily, after receiving these messages, the receiving end may map the SN carried in the message with a pointer (pointer, PTR) that can indicate a cache address of the receiving end at the granularity of the service (the SN corresponding to different services is mapped PTR is different). Subsequently, the sequencers corresponding to different services need to continuously detect whether the message corresponding to the current PTR of the service is received. If received, read the message in the buffer address corresponding to the current pointer, and then continue to detect the message corresponding to the next pointer. Whether the message is received. If not received, the receiver waits for the message. In this way, the sorter at the receiving end can sort the received packets at the granularity of the service.

Method 2: The sending end can insert a sending timestamp in the message sent to the receiving end. The sending time stamp is a global synchronization time stamp in the network. That is to say, each node in the network, for example, the sending end, the receiving end, and the nodes on each transmission path between the sending end and the receiving end are time-synchronized. After the sending end sends the message, the receiving end and each node in the transmission path sort the message according to the sending timestamp carried in the message.

Exemplarily, as shown in FIG. 2A, the data flow of PE 0 can be sent from PE 0 to PE 5 through LSP 201, LSP 202 and LSP 203. Among them, LSP 201 includes PE 1, PE 4 and PE 5. LSP 202 includes PE 2, PE 4 and PE 5. LSP 203 includes PE 3, PE 4 and PE 5. After PE 0 sends a packet, PE 1, PE 2, PE 3, PE 4, and PE 5 all sort the received packets according to the sending timestamp carried in the packet. Taking PE 4 as an example, after receiving packets from PE 1, PE 2, and PE 3, PE 4 can sort the received packets according to the sending timestamp, and then send the sorted packets to PE 5 in order . For example, as shown in Figure 2B, PE 4 can establish queues for packets from PE 1, PE 2, and PE 3 respectively. Among them, queue 1 is a queue established by PE 4 for packets from PE 1. Queue 2 is a queue established by PE 4 for packets from PE 2. Queue 3 is a queue established by PE 4 for packets from PE 3. Because PE 1, PE 2, and PE 3 have sorted the received packets before, the packets sent by PE 1, PE 2, and PE 3 are in order. In this case, PE 4 can compare the size of the sending timestamps carried by the packets currently output by each queue, and read the packets with smaller sending timestamps first, so that the packets can be sorted.

Method 3: The sending end may send the first message of the first service to the receiving end through the first path, and the first message carries the first sending timestamp. After the receiving end receives the first message through the first path, it can determine the first delay parameter according to the first maximum transmission delay of multiple paths, and obtain the first expected read time according to the first delay parameter and the first sending timestamp. Get the time, and read the data of the first message according to the first estimated read time. This method will be described in detail in the embodiment shown in FIG. 6 below, and will not be repeated here.

In order to facilitate the understanding of the method for transmitting packets described in the embodiment shown in FIG. 6 below, the principle of the method will be described first.

As mentioned above, the transmission delays of packets on different paths are different, so the packets received by the receiver are out of sequence. Then, after receiving the message, the receiving end can obtain the maximum transmission delay in different paths, obtain the estimated reading time of the message according to the sending timestamp and the maximum transmission delay, and then read the message according to this time. In this way, the order in which the receiving end reads the packets is consistent with the order in which the sending end sends the packets, that is, the packets read by the receiving end are in order.

Taking the network shown in Figure 2A as an example, as shown in Figure 3, PE 0 sends message 1 to PE 5 through LSP 201, and the sending timestamp carried in message 1 is time T1. After that, PE 0 sends message 2 to PE 5 through LSP 202, and the sending time stamp carried in message 2 is time T2. Afterwards, PE 0 sends message 3 to PE 5 through LSP 203, and the sending time stamp carried in message 3 is time T3. Wherein, T1=2 nanoseconds (ns), T2=4ns, T3=6ns. If PE 5 receives message 2 at time T4, receives message 3 at time T5, and receives message 1 at time T6, wherein, T4=5ns, T5=7ns, T6=8ns, then the transmission of message 1 The time delay is T6-T1=6ns, the transmission time delay of message 2 is T4-T2=1ns, and the transmission time delay of message 3 is T5-T3=1ns. It can be seen from this that among LSP 201, LSP 202 and LSP 203, LSP 201 has the largest transmission delay. The receiving end can use the sum of the sending timestamp of the message and the maximum transmission delay in multiple paths as the expected reading time of the message. For example, the expected reading time of message 1 is T6=T1+6=8ns, the expected reading time of message 2 is T7=T2+6=10ns, and the expected reading time of message 3 is T8=T3+6=12ns. In this way, the packets read by the receiving end according to the estimated read time are in order. Compared with the relative positional relationship on the time axis of the message read by the receiving end and the relative positional relationship on the time axis of the message sent by the sending end, there is no change, and it is a delay translation on the time axis.

Compared with method 1, the method shown in Figure 6 does not require packets to be sorted at the granularity of services, but can sort the received packets as a whole without distinguishing services. Therefore, the method shown in Figure 6 does not need to prepare a corresponding sorter for each service, that is, in the method shown in Figure 6, in order to achieve the sorting of packets, there is no need to schedule multiple sorters, which can reduce the reception The complexity of the terminal can also reduce the consumption of computing resources and storage resources. In addition, the receiving end only needs to read the message according to the expected reading time of the message, and there is no need to introduce aging time (that is, the time for the receiving end to wait for the message), which can reduce the delay jitter.

Compared with method 2, the method shown in FIG. 6 does not require time synchronization of each node in the network, and does not require all nodes in the transmission path to sort packets. In the method shown in FIG. 6 , the receiving end only needs to sort the received messages, which has low requirements on the network and is easy to implement.

As shown in FIG. 4 , it is a schematic structural diagram of a communication system 40 provided in the embodiment of the present application. In FIG. 4 , a communication system 40 may include a sending end 401 , a receiving end 402 and a network 403 . The sending end 401 and the receiving end 402 can communicate through the network 403 . For example, a packet sent by the sending end 401 may reach the receiving end 402 through multiple paths in the network 403 .

The sending end 401 or the receiving end 402 in FIG. 4 may be a computer, or a device with a sending and receiving function. For example, the sending end 401 or the receiving end 402 may be a portable computer (such as a mobile phone), a notebook computer, a personal computer (personal computer, PC), a wearable electronic device (such as a smart watch), a tablet computer, and the like. The sending end 401 or the receiving end 402 may also be a device capable of providing services such as computing or applications. It can be understood that the sending end 401 or the receiving end 402 may also be called a terminal device, a user end, a client, a user equipment, a mobile station, a mobile station or a server, and the like.

The network 403 in FIG. 4 may also be called a transmission network, and may be used to transmit data between the sending end 401 and the receiving end 402 . Exemplarily, the network 403 includes multiple paths, any of which may be used to transmit the data sent by the sending end 401 to the receiving end 402 . Any one of the paths may include at least one node, and the node may forward the data sent by the data sending end 401 , so that the data sent by the sending end 401 can reach the receiving end 402 .

The communication system 40 shown in FIG. 4 is only used as an example, and is not used to limit the technical solution of the present application. Those skilled in the art should understand that in a specific implementation process, the communication system 40 may also include other devices, and the number of sending ends and receiving ends may also be determined according to specific needs, without limitation. For example, the communication system may further include a sending end 404 . The sending end 404 can communicate with the receiving end 402 through the network 403 .

Optionally, each device (such as the receiving end 402, etc.) in FIG. .

Optionally, the relevant functions of each device (such as the receiving end 402) in FIG. The functional modules are implemented, which is not specifically limited in this embodiment of the present application. It can be understood that the above-mentioned functions can be network elements in hardware devices, software functions running on dedicated hardware, or a combination of hardware and software, or instantiated virtualization on a platform (for example, a cloud platform) Function.

During specific implementation, each device shown in FIG. 4 may adopt the composition structure shown in FIG. 5 , or include components shown in FIG. 5 . FIG. 5 is a schematic diagram of a hardware structure of a communication device applicable to an embodiment of the present application. The communication device 50 includes at least one processor 501 and at least one communication interface 504, configured to implement the method provided in the embodiment of the present application. The communication device 50 may also include a communication line 502 and a memory 503 .

The processor 501 can be a general-purpose central processing unit (central processing unit, CPU), a microprocessor, a specific application integrated circuit (application-specific integrated circuit, ASIC), or one or more for controlling the execution of the application program program integrated circuit.

Communication line 502 may include a path, such as a bus, for transferring information between the aforementioned components.

The communication interface 504 is used for communicating with other devices or a communication network. The communication interface 504 can be any device such as a transceiver, such as an Ethernet interface, a wireless access network (radio access network, RAN) interface, a wireless local area network (wireless local area networks, WLAN) interface, a transceiver, a pin , bus, or transceiver circuits, etc.

The memory 503 may be a read-only memory (read-only memory, ROM) or other types of static storage devices that can store static information and instructions, a random access memory (random access memory, RAM) or other types that can store information and instructions It can also be an electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or can be used to carry or store desired program code in the form of instructions or data structures and can be programmed by a computer Any other medium accessed, but not limited to. The memory may exist independently and be coupled with the processor 501 through the communication line 502. The memory 503 can also be integrated with the processor 501 . The memory provided by the embodiment of the present application may generally be non-volatile. Wherein, the memory 503 is used to store computer-executed instructions involved in implementing the solutions provided by the embodiments of the present application, and the execution is controlled by the processor 501 . The processor 501 is configured to execute computer-executed instructions stored in the memory 503, so as to implement the method provided in the embodiment of the present application.

The computer-executed instructions in the embodiments of the present application may also be referred to as application program codes, which is not specifically limited in the embodiments of the present application.

The coupling in the embodiments of the present application is an indirect coupling or a communication connection between devices, units or modules, which may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules.

As an embodiment, the processor 501 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 5 .

As an embodiment, the communication device 50 may include multiple processors, for example, the processor 501 and the processor 507 in FIG. 5 . Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).

As an embodiment, the communication device 50 may further include an output device 505 and/or an input device 506 . Output device 505 is coupled to processor 501 and can display information in a variety of ways. For example, the output device 505 may be a liquid crystal display (liquid crystal display, LCD), a light emitting diode (light emitting diode, LED) display device, a cathode ray tube (cathode ray tube, CRT) display device, or a projector (projector) Wait. The input device 506 is coupled to the processor 501 and can receive user input in various ways. For example, the input device 506 may be a mouse, a keyboard, a touch screen device, or a sensing device, among others.

It can be understood that the composition structure shown in FIG. 5 does not constitute a limitation to the communication device. In addition to the components shown in FIG. 5, the communication device may include more or less components than shown in the figure, or combine some components, or a different arrangement of components.

The following uses the architecture shown in FIG. 4 as an example to describe the method for transmitting a packet provided by the embodiment of the present application. Each device in the following embodiments may have the components shown in FIG. 5 , which will not be described in detail.

It should be noted that, in this embodiment of the present application, transmission may be understood as sending and/or receiving according to a specific context. Transfer can be a noun or a verb. Transmission is often used instead of sending and/or receiving when the subject of the action is not emphasized. For example, the phrase transmission message can be understood as sending a message from the perspective of the sender, and can be understood as receiving a message from the perspective of the receiver.

It should be noted that the names of the messages between devices or the names of the parameters in the messages in the following embodiments of the present application are just examples, and other names may also be used in specific implementations, which are not specifically limited in the embodiments of the present application. .

In order to facilitate the description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" may be used to distinguish technical features with the same or similar functions. The words "first" and "second" do not limit the number and execution order, and the words "first" and "second" do not necessarily mean that they must be different. In the embodiments of this application, words such as "exemplary" or "for example" are used to represent examples, illustrations or illustrations, and any embodiment or design described as "exemplary" or "for example" should not be interpreted It is more preferred or more advantageous than other embodiments or design solutions. The use of words such as "exemplary" or "for example" is intended to present related concepts in a specific manner for easy understanding.

It should be noted that, in the embodiment of the present application, for a technical feature, "first", "second", "third", "A", "B", "C" and "D" etc. To distinguish the technical features of this type of technical features, the technical features described by the "first", "second", "third", "A", "B", "C" and "D" are in no order or order of size.

It can be understood that, in the embodiments of the present application, the same step or steps or technical features having the same function can be used for reference in different embodiments.

It can be understood that in the embodiment of the present application, the receiving end may perform some or all of the steps in the embodiment of the present application, these steps are only examples, and the embodiment of the present application may also perform other steps or variations of various steps. In addition, each step may be performed in a different order presented in the embodiment of the present application, and it may not be necessary to perform all the steps in the embodiment of the present application.

In the embodiment of the present application, the specific structure of the execution subject of the method for transmitting the message is not limited, as long as the method provided in the embodiment of the present application can be realized. For example, the execution subject of the method for transmitting a message provided in the embodiment of the present application may be the receiving end, or a component applied to the receiving end, for example, a chip system, which is not limited in the present application. In the embodiment of the present application, the system-on-a-chip may be composed of chips, or may include chips and other discrete devices. The following embodiments are described by taking the execution subject of the method for transmitting a message as the receiving end as an example.

As shown in FIG. 6 , it is a method for transmitting a message provided in the embodiment of the present application, and the method for transmitting a message includes S601-S604.

S601: The sending end sends the first packet of the first service to the receiving end through the first path. Correspondingly, the receiving end receives the first packet of the first service sent by the sending end through the first path.

Wherein, the sending end may be the sending end 401 in FIG. 4 . The receiving end may be the receiving end 402 in FIG. 4 . The first path is one of multiple paths for transmitting the packet of the first service to the receiving end. The first service is one of multiple services of the sending end.

In this embodiment of the present application, the first packet carries the first sending timestamp and data of the first packet. Wherein, the first sending time stamp corresponds to the time when the first message is sent in the time domain of the sending end, or in other words, the first sending time stamp is used to indicate the time when the first message is sent in the time domain of the sending end. For example, when the sender generates the first packet, the time when the first packet is generated is used as the first sending timestamp to represent the time when the first packet is sent in the time domain of the sender.

It can be understood that the accuracy of the sending time stamp inserted by the sending end into the message of the first service can meet the following requirements: the sending time stamps of two adjacent messages are not repeated, and the time increment relationship is satisfied. In addition, the accuracy of the sending time stamp can also satisfy: the maximum bandwidth of the data that does not affect the sending message. Taking the implementation of the binary chip as an example, the precision of sending the time stamp can be 1/(2^n)ns, for example, 1/8ns. The bit width of the sending timestamp can meet the requirement of recording the maximum delay of the network without inversion, for example, the maximum support is 1 second (s) delay.

S602: The receiving end obtains a first delay parameter of the first service.

In a possible implementation manner, the first delay parameter is determined according to a first maximum transmission delay of multiple paths between the sending end and the receiving end. Wherein, the multiple paths between the sending end and the receiving end may include all paths between the sending end and the receiving end, or may include part of the paths between the sending end and the receiving end. If the multiple paths between the sending end and the receiving end include a partial path between the sending end and the receiving end, the partial path includes multiple paths for transmitting the packet of the first service to the receiving end.

Exemplarily, if all the paths between the sending end and the receiving end include path 1-path 5, wherein, path 1-path 3 are used to transmit packets of the first service, then multiple paths between the sending end and the receiving end The path may include path 1-path 3, or path 1-path 4, or path 1-path 5, or path 1-path 3 and path 5.

Exemplarily, the first delay parameter is determined according to the first maximum transmission delay and the first margin. For example, the first delay parameter is the sum of the first maximum transmission delay and the first margin; or, the first delay parameter is the product of the first maximum transmission delay and the first margin. Wherein, the first margin may also be referred to as a safety compensation value, a compensation value, etc., without limitation. The first margin is a positive number. The first margin may be set by the user, or may be a default default value. In a specific application, the user can modify the first margin according to specific conditions.

In the embodiment of the present application, the first maximum transmission delay is an estimated value, which is used to represent the maximum transmission delay of multiple paths between the sending end and the receiving end. Exemplarily, the receiving end can obtain the first maximum transmission delay in at least the following two ways.

Method 1: The receiving end obtains the first maximum transmission delay according to the transmission delays of multiple paths in history.

In a possible implementation manner, the receiving end determines a maximum value of transmission delays of multiple paths between the sending end and the receiving end within a period of time as the first maximum transmission delay. For example, the receiving end determines the maximum value of the transmission delays of multiple paths between the sending end and the receiving end within one month as the first maximum transmission delay. In mode 1, the first maximum transmission delay is a fixed value. Unless reset, usually the first maximum transmission delay remains unchanged.

Method 2: The receiving end takes the service as the granularity and makes statistics on a periodic basis to obtain the first maximum transmission delay.

In a possible implementation, in one period, the receiving end counts the transmission delays of the packets of the first service on multiple paths between the sending end and the receiving end, and calculates the maximum transmission time of the multiple paths currently counted. Delay is determined as the first maximum transmission delay. For mode 2, the first maximum transmission delay is a variable value, which may change according to the statistical results. That is, the receiving end can dynamically adjust the first maximum transmission delay, or in other words, the receiving end can count the first maximum transmission delay in real time.

Exemplarily, when the receiving end receives the packet 1 of the first service at the beginning of the period, and the transmission delay of the packet 1 is 2 ns, the receiving end determines that the first maximum transmission delay is 2 ns. After receiving packet 1, the receiving end receives packet 2 of the first service, and the transmission delay of packet 2 is 1 ns, so the receiving end determines that the first maximum transmission delay is 2 ns. After receiving packet 2, the receiving end receives packet 3 of the first service, and the transmission delay of packet 3 is 3 ns, so the receiving end determines that the first maximum transmission delay is 3 ns.

For method 2, the pseudo code for the receiving end to obtain the first maximum transmission delay can be as follows:

Among them, Tr is the time when the receiving end receives the first message, Tsr corresponds to the time when the sending end sends the first message in the time domain of the receiving end, Td is the transmission delay of the first message, and Tdamx is the first Maximum transmission delay. The pseudo-code above describes the following process: 1. Calculate the transmission delay of the first message; 2. If the transmission delay of the first message is greater than the latest first maximum transmission delay, the transmission time of the first message The delay is determined as the first maximum transmission delay; 3. After the statistics period ends, the first maximum transmission delay is set to 0.

It can be understood that the first maximum transmission delay is an estimated value, and the estimation may be inaccurate. In order to avoid the situation that the estimated maximum transmission delay of multiple paths is small and cause packet sorting errors, a compensation value (that is, the first margin) can be set to try to make the first maximum after compensation according to the compensation value The transmission delay (that is, the first delay parameter) is greater than or equal to the maximum transmission delay of multiple paths.

In a possible implementation manner, if the difference between the first delay parameter and the first maximum transmission delay is greater than the first threshold and lasts for a first time, it indicates that the current first delay parameter is too large. In this case, the receiving end may adjust the first delay parameter. For example, the receiving end may call back the first delay parameter in small steps multiple times. The value of each callback can be less than the minimum time interval for the sender to send messages to avoid packet disorder caused by callbacks.

In a possible implementation manner, after S604, the receiving end may also detect whether the sequence of the first packet is correct. If the receiving end detects that the ordering of the first packet is wrong, it means that the current first delay parameter is too small. In this case, the receiving end may adjust the first delay parameter. For example, the receiving end may increase the first delay parameter by the second margin. The process for the receiving end to detect whether the sorting of the first packet is correct will be introduced after S604, and will not be repeated here.

To sum up, the pseudocode of the dynamic adjustment of the first delay parameter at the receiving end can be as follows:

Wherein, Tc is the first delay parameter, Tgd is the first margin, Tfb is the second margin, and Tb is the value of each callback. The callback condition is if Tc-Tdmax>Tgd, and it lasts for X milliseconds (ms). It can be understood that the above Tc=Tc+Tfb is an expression of a code, which is used to indicate that Tc is adjusted. The first Tc is the first time delay parameter after adjustment, and the second Tc is the first time delay parameter before adjustment. Similarly, the above-mentioned Tc=Tc-Tb is also an expression of a code, which is used to indicate that Tc is adjusted. The first Tc is the first time delay parameter after adjustment, and the second Tc is the first time delay parameter before adjustment. The above pseudo code describes the following process: if Tc<(Tdmax+Tgd), then determine Tdmax+Tgd as the first delay parameter; or, if the receiving end detects that the first packet is incorrectly sorted, then determine Tc+Tfb is the first delay parameter; or, if the callback condition is met, Tc-Tb is determined as the first delay parameter.

S603: The receiving end obtains a first estimated read time according to the first sending timestamp and the first delay parameter.

Wherein, the first expected reading time may be the time when the receiving end expects to read the first packet.

In this embodiment of the present application, the receiving end and the sending end may or may not be synchronized in the time domain. If the receiving end and the sending end are synchronized in the time domain, the receiving end may add the first sending timestamp and the first delay parameter to obtain the first expected reading time. If the receiving end and the sending end are not synchronized in the time domain, the receiving end can perform time domain mapping between the sending end and the receiving end first, unify the time domains of the receiving end and the sending end, and then map the time domain on the unified time domain Get the first estimated read time. Specifically, the receiving end may map the first sending time stamp to the time domain of the receiving end to obtain the second sending time stamp, and obtain the first expected read time according to the second sending time stamp and the first delay parameter. Wherein, the second sending time stamp corresponds to the time when the sending end sends the first message in the time domain of the receiving end, or in other words, the second sending time stamp is used to indicate that in the time domain of the receiving end, the time when the sending end sends the first message text time.

The specific method of time domain mapping is as follows: the receiving end obtains the second sending time stamp according to the first sending time stamp, the first reference time stamp, the second reference time stamp and the first clock mapping parameter. Wherein, the first reference time stamp is the time corresponding to the first moment in the time domain of the sending end. The second reference time stamp is the time corresponding to the first moment in the time domain of the receiving end.

Exemplarily, the calculation method is as follows: T _sr1 =T _sr0 +K _sr0 *(T _s1 -T _s0 ), or, T _sr1 =T _sr0 +K _sr0 *(T _s1 -T _s0 )+C. Among them, T _sr1 is the second transmission time stamp, T _sr0 is the second reference time stamp, K _sr0 is the first clock mapping parameter, T _s1 is the first transmission time stamp, T _s0 is the first reference time stamp, and C is the adjustment parameter.

For the situation that the receiving end and the sending end are not synchronized in the time domain, before S603, the receiving end can obtain the first reference time stamp, the second reference time stamp and the first clock mapping parameter, and the receiving end can further obtain the second sending The time stamp is not limited in this application.

In this embodiment of the application, if the first message is the first message received by the receiving end from the sending end, the first reference time stamp, the second reference time stamp and the first clock mapping parameter may be an initialized value . The initialized value can be configured by the user or the receiving end. For example, if the first message is the first message received by the receiving end from the sending end, the first reference time stamp and the second reference time stamp are 0, and the first clock mapping parameter is 1. If the first message is not the first message from the sender received by the receiver, the first reference time stamp may correspond to the time stamp of the message sent by the sender before sending the first message in the time domain of the sender For sending time, the second reference time stamp may be a time stamp obtained by mapping the first reference time stamp to the time domain of the receiving end, and the first clock mapping parameter may be a parameter after at least one dynamic adjustment of the initialized clock mapping parameter. For the process of dynamically adjusting the clock mapping parameters at the receiving end each time, you can refer to the following introduction of adjusting the first clock mapping parameters at the receiving end to obtain the second clock mapping parameters, which will not be repeated here.

It can be understood that, in order to make the time domain mapping between the sending end and the receiving end more accurate, the receiving end may adjust the first clock mapping parameter to obtain the second clock mapping parameter after obtaining the second sending timestamp. Subsequently, the receiving end may perform time-domain mapping between the sending end and the receiving end according to the second clock mapping parameter.

In a possible implementation manner, after S603, the receiving end adjusts the first clock mapping parameter according to the first transmission delay, the second transmission delay and the adjustment factor, so as to obtain the second clock mapping parameter. In this case, the first moment corresponds to the time when the sending end sends the third packet of the first service to the receiving end through the first path. The first transmission delay is the transmission delay of the first packet from the sending end to the receiving end, and the second transmission delay is the transmission delay of the third packet from the sending end to the receiving end.

Exemplarily, the second clock mapping parameter satisfies the formula: K _sr1 =K _sr0 +K _c *T _dc1 . Wherein, K _sr1 is the second clock mapping parameter, K _sr0 is the first clock mapping parameter, K _c is the adjustment factor, and T _dc1 satisfies the formula: T _dc1 =(T _r1 -T _sr1 )-(T _r0 -T _sr0 ). Wherein, T _r1 is the time when the receiving end receives the first message, T _sr1 is the second sending time stamp, T _r0 is the time when the receiving end receives the third message, and T _sr0 is the second reference time stamp. In the embodiment of the present application, if the clock tracking range is <150ppm, K _c may be set to K _c =150/(10^6*1000).

To sum up, the pseudo code for time-domain mapping between the sender and receiver can be as follows:

Among them, Tsn is the first reference time stamp, Tsrn is the second reference time stamp, Krs is the clock mapping parameter, Tsr is the second transmission time stamp, Ts is the first transmission time stamp, Td is the first transmission delay, and Tdn is The second transmission delay, Kc is an adjustment factor. It can be understood that the above-mentioned Krs=Krs+Kc*Tdc is an expression of the code, which is used to indicate that Krs is adjusted. The first Krs is the adjusted clock mapping parameter, and the second Krs is the clock mapping parameter before adjustment. Similarly, the above-mentioned Tsrn=Tsrn+Td is also an expression of the code, which is used to indicate that Tsrn is adjusted. The first Tsrn is the adjusted second reference time stamp, and the second Tsrn is the second reference time stamp before adjustment. The pseudo-code above describes the following process: the initialization value of Tsn and Tsrn is 0, and the initialization value of Krs is 1; Krs*(Ts-Tsn) obtains the second sending timestamp, and calculates Td and Tdc; if Ts is obtained later than Tsn, then make Tsrn=Tsr, Tsn=Ts, Krs=Krs+Kc*Tdc, Tdn=Td; Td represents the transmission delay, which should be a positive value under normal circumstances. If Td<0 obtained by the above method, the receiving end can adjust Tsrn so that Td>0. For example, the receiving end may set Tsrn=Tsrn+Td.

It can be seen from the above description that the receiving end can set the initial value of Krs to 1, and then dynamically adjust Krs through Tdc, so that Krs tends to be stable. For example, make the final limit of Krs within the range of plus or minus 150ppm.

Understandably, if Krs is accurate, Tdc will approach zero. Therefore, if Tdc gradually increases, it means that Krs is small, and Krs can be increased appropriately; if Tdc gradually decreases, it means that Krs is large, and Krs can be appropriately reduced. By adjusting Krs dynamically, a more accurate Krs can be obtained.

In a possible implementation manner, if the first expected reading time is less than the current time, it means that the time for reading the first packet has passed, and the receiving end may discard the first packet.

In a possible implementation manner, if the difference between the first expected reading time and the current time is greater than the first time length, the receiving end discards the first packet. Wherein, the first time length is the packet out-of-sequence time that the receiving end can support, or in other words, the receiving end can sort the packets sent within the first time length. For example, if the first time length is 6ms and the current time is 1ms, then the receiving end can sort the packets whose expected reading time is 1ms-7ms. If the first expected reading time is 8ms, it exceeds the sorting capability of the receiving end. In this case, the receiving end discards the first packet, or the receiving end may also cache the first packet, and then sort the first packets when the current time is 2 ms.

S604: The receiving end reads the data of the first packet according to the first expected reading time.

In a possible implementation manner, the receiving end reads the data of the first message according to the first expected reading time, including: in the multiple queues sorted by time, the receiving end sends the first message according to the first expected reading time Enqueue the file; when the first expected reading time has been reached or exceeded, and multiple queues indicate that it is the turn to read the data of the first message, read the data of the first message.

First, the multiple queues are described in detail.

In the embodiment of the present application, each of the multiple queues corresponds to a time difference interval, and the multiple queues are sorted according to the time difference interval. Taking three queues as an example, if the time difference interval corresponding to queue 1 is [0ns, 0.5ns], the time difference interval corresponding to queue 2 is (0.5ns, 1ns], and the time difference interval corresponding to queue 3 is ( 1ns, 1.5ns], when the receiving end reads the message, it can first read the message in queue 1, then read the message in queue 2, and finally read the message in queue 3. In this way, the receiving end After the received messages are queued, the received messages are sorted. Subsequently, the receiving end can read the data of the messages in the order of the queue output messages. It is understandable that the time difference corresponding to the queue The interval is configured by the receiver or the user. The time difference interval can be modified after configuration.

In the embodiment of the present application, the time difference interval corresponding to the queue may be used by the receiving end to enqueue the received message into the queue. Exemplarily, after the receiving end obtains the expected reading time of the message, it can obtain the difference between the expected reading time and the current time, and input the data of the message into the time difference interval corresponding to the difference. in queue. Wherein, the time difference interval where the difference is located can be understood as: the difference is greater than or equal to the minimum value of the time difference interval where the difference is located, and the difference is less than or equal to the minimum value of the time difference interval where the difference is located. maximum value.

In a possible implementation, the receiving end enqueues the first message according to the first estimated reading time, including: the receiving end inputs the information of the first message according to the difference between the first estimated reading time and the current time first queue. Wherein, the information of the first packet may include information related to the first packet. For example, the information of the first message includes the first message; or, the information of the first message includes the storage address of the first message at the receiving end; or, the information of the first message includes the storage address of the first message at the receiving end address and first sent timestamp. The information of the first packet may also be referred to as a packet descriptor of the first packet. It can be understood that if the information of the first message includes the first message, the receiving end reads the data of the first message from the queue; if the information of the first message includes the storage address of the first message at the receiving end, Then the receiving end reads the data of the first packet from the storage address. The multiple queues include a first queue, and the difference between the first expected reading time and the current time belongs to the time difference interval corresponding to the first queue.

Exemplarily, multiple queues at the receiving end may be as shown in FIG. 7A . In Fig. 7A, multiple queues include queue 701, queue 702, queue 703..., wherein, the time difference interval corresponding to queue 701 is [0ns, 1ns], and the time difference interval corresponding to queue 702 is (1ns, 2ns] , the time difference interval corresponding to the queue 703 is (2ns, 3ns]. If the difference between the first expected read time and the current time is 1ns, then the first queue is the queue 701; if the first expected read time and the current time If the difference between the first expected reading time and the current time is 2.5 ns, then the first queue is queue 703 .

In a possible implementation, if information of the second message is also stored in the first queue, the receiving end determines the first message and the second message according to the first expected read time and the expected read time of the second message. The position of the packet in the first queue. Exemplarily, if the first expected reading time is earlier than the expected reading time of the second message, the time when the information of the first message is output from the first queue is earlier than the time when the information of the second message is output from the first queue or, if the first expected read time is later than the expected read time of the second message, the time when the information of the first message is output from the first queue is later than the time when the information of the second message is output from the first queue Time for a queue output.

In this embodiment of the application, the second message may be other messages of the first service other than the first message sent by the sender, messages of other services sent by the sender, or messages sent by other senders .

It can be understood that in the embodiment of the present application, the sorting of packets by the receiving end does not require the granularity of services, and the received packets can be sorted as a whole without distinguishing between services. In this way, the complexity of the receiving end can be reduced, and for any service, its message is also in order, without affecting the function of the service. In addition, whether the receiving end reads the message is related to the expected reading time of the message and whether the message is located at the output port of the queue, and is not limited by other conditions. Therefore, the abnormal time stamp of a certain service does not affect the receiving end to read the messages of other services, and the reliability is high.

It should be understood that in the embodiment of the present application, the receiving end may also sort the received packets at the granularity of services, which is not limited.

In the embodiment of the present application, multiple queues are connected in series in the time domain, that is, information in the queues can be output from one queue and input to another queue as time goes by.

A possible implementation, if the difference between the first expected reading time and the current time is less than the minimum value of the time difference interval corresponding to the first queue, the receiving end outputs the information of the first message from the first queue , input to the second queue. Wherein, the second queue is included in multiple queues, and the difference between the first expected reading time and the current time belongs to the time difference interval corresponding to the second queue. It can be understood that the value in the time difference interval corresponding to the second queue is smaller than the value in the time difference interval corresponding to the first queue, or in other words, compared with the expected reading time of the message in the first queue, the second The expected reading time of the packets in the queue is closer to the current time.

Exemplarily, taking the queue shown in FIG. 7A as an example, the queue 701 , the queue 702 and the queue 703 are connected in series in the time domain. If the current time is time 1, and the difference between the first estimated read time and time 1 is 2.5 ns, then the receiving end will input the information of the first message into the queue 703 corresponding to the time difference interval of 2.5 ns. After a period of time, the current time becomes time 2, the difference between the first estimated reading time and time 2 is 2ns, and if 2ns is less than the minimum value of the time difference interval corresponding to the queue 703, the receiving end sends the first message The information of is output from the queue 703 and input into the queue 702 corresponding to the time difference interval of 2ns. After another period of time, the current time becomes time 3, and the difference between the first estimated reading time and time 3 is 1 ns, and if 1 ns is less than the minimum value of the time difference interval corresponding to the queue 702, the receiving end will send the first report The text information is output from the queue 702 and input into the queue 701 corresponding to the time difference interval where 1 ns is located.

In a possible implementation manner, the multiple queues are divided into multiple groups, each group includes at least one queue, and the lengths of the time difference intervals corresponding to the queues in different groups are different. Wherein, the length of the time difference interval may be the difference between the maximum value of the time difference interval and the minimum value of the time difference interval. Taking the queue 701 in FIG. 7A as an example, the time difference interval corresponding to the queue 701 is [0 ns, 1 ns], and the length of the time difference interval corresponding to the queue 701 is 1 ns-0 ns=1 ns.

Exemplarily, taking the above-mentioned first queue and the second queue as examples, if the first queue is included in the first group of queues and the second queue is included in the second group of queues, then the queues in the first group of queues The length of the corresponding time difference interval is greater than the length of the time difference interval corresponding to the queues in the second group of queues. It can be understood that among the multiple queues, the minimum value of the length of the time difference interval corresponding to the queue is smaller than the minimum time interval for sending packets by the sending end.

As shown in FIG. 7B , it is a schematic diagram of multiple queues. In Fig. 7B, multiple queues are divided into 4 groups. The length of the time difference interval corresponding to the queue in queue group 1 is 1/8ns, the length of the time difference interval corresponding to the queue in queue group 2 is 16ns, and the length of the time difference interval corresponding to the queue in queue group 3 is 1 microsecond (us), and the length of the time difference interval corresponding to the queue in queue group 4 is 64 us. The first group of queues can be queue group 2, and the second group of queues can be queue group 1; or, the first group of queues can be queue group 3, and the second group of queues can be queue group 2; the first group of queues The column can be Queue Group 4 and the second set of queues can be Queue Group 3.

It can be understood that configuring different time difference interval lengths for different groups of queues can greatly reduce the number of queues and reduce the complexity of queue maintenance at the receiving end. Exemplarily, taking the first time length (that is, the packet out-of-sequence time that the receiving end can support, and the sum of the lengths of the time difference intervals corresponding to multiple queues) as an example, if the time difference corresponding to each queue The length of the value interval is the same, both are 1ns, and the receiving end needs to maintain 8000000 queues. If the lengths of the time difference intervals corresponding to the queues in different groups are different, for example, multiple queues are divided into 4 groups, the length of the time difference intervals corresponding to the queues in the first group of queues is 1/8ns, and the length of the second The length of the time difference interval corresponding to the queues in the first group of queues is 16ns, the length of the time difference intervals corresponding to the queues in the third group of queues is 1us, and the length of the time difference intervals corresponding to the queues in the fourth group of queues length is 64us, then in the case that each group includes 128 queues, the sum of the lengths of the time difference intervals corresponding to multiple queues can be greater than 8ms. In this case, the receiving end needs to maintain 512 queues, which greatly reduces the complexity of the receiving end.

In a possible implementation, when the lengths of the time difference intervals corresponding to the queues in different groups are different, if the length of the time difference intervals corresponding to the first queue is greater than the second time length, then the receiving end will When the information of the message is input into the first queue, the position of the information of the first message in the first queue may not be determined, so as to reduce the calculation overhead of the receiving end. If the length of the time difference interval corresponding to the first queue is less than or equal to the second time length, the receiving end can determine the first message according to the first expected reading time when inputting the information of the first message into the first queue The position of the message in the first queue. Similarly, if the length of the time difference interval corresponding to the second queue is greater than the second time length, when the receiving end inputs the information of the first message into the second queue, it may not be sure that the information of the first message is in the second queue. position in the queue to reduce computational overhead on the receiving end. If the length of the time difference interval corresponding to the second queue is less than or equal to the second time length, the receiving end can determine the first message according to the first expected reading time when inputting the information of the first message into the second queue The position of the message in the second queue.

In a possible implementation manner, after S604, the receiving end detects whether the sequence of the first packet is correct.

As an example, the receiving end receives the fourth packet of the first service sent by the sending end, where the fourth packet carries a third sending time stamp, and the third sending time stamp corresponds to the time domain of the sending end. The time of the fourth message. The receiving end can compare the sizes of the first sending timestamp and the third sending timestamp to determine whether the sequence of the first packet is correct. For example, in the case that the fourth message is read latest before reading the first message, the third sending time stamp should be smaller than the first sending time stamp. If the comparison result is that the third sending timestamp is greater than the first sending timestamp, it may indicate that the ordering of the first packet is wrong. In case the fourth telegram is read most recently after reading the first telegram, the third transmission time stamp should be greater than the first transmission time stamp. If the comparison result is that the third sending timestamp is smaller than the first sending timestamp, it may indicate that the ordering of the first packet is wrong.

In a possible implementation manner, if the sequence of the first packet is wrong, the receiving end adjusts the first delay parameter. For example, the receiving end may increase the first delay parameter by a second margin, where the second margin is a positive number, and the second margin may be a difference between the third sending timestamp and the first sending timestamp.

In a possible implementation manner, if the sequence of the first packet is incorrect, the receiving end sends an alarm message. For example, if the sequence of the first message is wrong, the receiving end displays warning information on the human-computer interaction interface of the receiving end, so that the user can adjust relevant parameters according to the warning information. Or, if the sequence of the first message is incorrect, the receiving end sends an alarm message to the server, so that the administrator can perform related processing according to the alarm message.

It can be understood that the foregoing S601-S604 are described based on a packet received by the receiving end. The receiving end can perform the above S601-S604 on the received packets, so as to sort the received packets. For example, as shown in Figure 8, if the receiving end and the sending end are synchronized in the time domain, after receiving a new message, the receiving end can use the time stamp Tsr carried in the new message, the The receiving time Tr of the new message and the current statistical maximum transmission delay Tdmax obtain the delay parameter Tc, and the receiving end can also adjust Tdmax and Tc to make Tdmax and Tc more accurate. Subsequently, the receiving end can obtain the expected reading time of the new message according to Tc and Tsr, and read the data of the new message according to the expected reading time. If the receiving end and the sending end are not synchronized in the time domain, after receiving the new message, the receiving end can transmit the time stamp Ts carried in the new message, the sending time stamp Tsn and Tsn of the previously received message The sending timestamp Tsrn and the clock mapping parameter Krs mapped to the time domain of the receiving end are obtained, and the sending timestamp Tsr mapped from Ts to the time domain of the receiving end is obtained, and the receiving end can also adjust Tsn, Tsrn and Krs. Subsequently, the receiving end can obtain Tc according to Tsr, the receiving time Tr of the new message received by the receiving end, and the current statistical maximum transmission delay Tdmax, and obtain the estimated reading time of the new message according to Tc and Tsr, according to Estimated read time to read the data of this new message.

It can be understood that the receiving end may receive messages from different sending ends, and for different sending ends, the receiving end uses different clock mapping parameters when performing time domain mapping. However, the receiving end sorts the received packets as a whole, and the sending end may not be distinguished.

Based on the method shown in Figure 6, after the receiving end receives the first message of the first service from the sending end through the first path, it can obtain the first delay parameter according to the first maximum transmission delay of multiple paths, according to The first delay parameter obtains the estimated time to read the data of the first packet, and reads the data of the first packet according to the estimated time to read the data of the first packet, so as to realize the sorting of the first packets. Through the method shown in Figure 6, the receiving end can sort the received messages as a whole without distinguishing services, which can reduce the complexity of the receiving end and reduce the consumption of computing resources and storage resources. Moreover, for any service, its packets are also in order, which does not affect the function of the service. In the process of sorting, the receiving end reads the data of the message according to the expected time to read the data of the message. The abnormal time stamp of a certain service does not affect the receiving end to read the data of other service messages, and the reliability is high. . The method shown in FIG. 6 also does not need to introduce aging time, and can reduce delay jitter. In addition, the method shown in Figure 6 has no special requirements on the transmission network, and can be deployed at the sending end and the receiving end, which is easy to implement.

The actions of the receiving end in S601-S604 above can be executed by the processor 501 in the communication device 50 shown in FIG. 5 calling the application program code stored in the memory 503, which is not limited in this embodiment of the present application.

The foregoing mainly introduces the solution provided by the embodiment of the present application from the perspective of interaction between various network elements. Correspondingly, the embodiment of the present application also provides a communication device, which may be the receiving end in the above method embodiments, or a device including the above receiving end, or a component that may be used for the receiving end. It can be understood that, in order to realize the above functions, the communication device includes hardware structures and/or software modules corresponding to each function. Those skilled in the art should easily realize that the present application can be implemented in the form of hardware or a combination of hardware and computer software in combination with the units and algorithm steps of each example described in the embodiments disclosed herein. Whether a certain function is executed by hardware or computer software drives hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

FIG. 9 shows a schematic structural diagram of a communication device 90 . The communication device 90 includes a receiving module 901 and a processing module 902 . The receiving module 901 may also be referred to as a receiving unit to implement a receiving function, for example, it may be a receiving circuit, a receiver, a receiver or a communication interface.

Wherein, taking the communication device 90 as the receiving end in the above method embodiment as an example:

The receiving module 901 is configured to receive the first packet of the first service sent by the sending end through the first path, the first packet carries a first sending timestamp, and the first sending timestamp corresponds to the time domain of the sending end. At the time of the first packet, the first path is one of multiple paths for transmitting the packet of the first service to the receiving end. Exemplarily, with reference to FIG. 6 , the receiving module 901 may be used to instruct S601.

The processing module 902 is configured to obtain a first delay parameter of the first service, where the first delay parameter is determined according to first maximum transmission delays of multiple paths. Exemplarily, with reference to FIG. 6 , the processing module 902 may be used to execute S602.

The processing module 902 is further configured to obtain a first expected read time according to the first sending time stamp and the first delay parameter. Exemplarily, with reference to FIG. 6 , the processing module 902 may be used to execute S603.

The processing module 902 is further configured to read the data of the first message according to the first expected reading time. Exemplarily, with reference to FIG. 6 , the processing module 902 may be used to execute S603.

Optionally, the processing module 902 is specifically configured to enqueue the first message according to the first expected read time in multiple queues sorted by time; When the reading time is estimated and multiple queues indicate that it is the turn to read the data of the first message, the data of the first message is read.

Optionally, the processing module 902 is further specifically configured to input the information of the first message into the first queue according to the difference between the first estimated reading time and the current time, and the difference between the first estimated reading time and the current time It belongs to the time difference interval corresponding to the first queue.

Optionally, the information of the second message is also stored in the first queue. If the first expected read time is earlier than the expected read time of the second message, the information of the first message is output from the first queue. Time, earlier than the time when the information of the second message is output from the first queue; or, if the first expected read time is later than the expected read time of the second message, the information of the first message is output from the first queue The output time is later than the time when the information of the second packet is output from the first queue.

Optionally, the second message is other messages of the first service sent by the sender except the first message, messages of other services sent by the sender, or messages sent by other senders.

Optionally, the processing module 902 is further configured to transfer the information of the first message from the first The output of the queue is input to the second queue, the second queue is included in multiple queues, and the difference between the first expected reading time and the current time belongs to the time difference interval corresponding to the second queue.

Optionally, multiple queues are divided into multiple groups, the first queue is included in the first group of queues, the second queue is included in the second group of queues, and the time difference intervals corresponding to the queues in the first group of queues The length is greater than the length of the time difference interval corresponding to the queues in the second group of queues.

Optionally, the processing module 902 is specifically configured to map the first sending timestamp to the time domain of the receiving end to obtain the second sending timestamp; the processing module 902 is also specifically configured to The delay parameter gets the first estimated read time.

Optionally, the processing module 902 is further configured to obtain a first reference time stamp, a second reference time stamp, and a first clock mapping parameter, where the first reference time stamp is the time corresponding to the first moment in the time domain of the sending end, The second reference time stamp is the time corresponding to the first moment in the time domain of the receiving end; the processing module 902 is also specifically configured to Mapping parameters to obtain the second sending timestamp.

Optionally, the first moment corresponds to the time when the sending end sends the third packet of the first service to the receiving end through the first path, and the processing module 902 is further configured to, according to the first transmission delay, the second transmission delay and The adjustment factor is to adjust the first clock mapping parameter. The first transmission delay is the transmission delay of the first message from the sending end to the receiving end, and the second transmission delay is the transmission time of the third message from the sending end to the receiving end. delay.

Optionally, the receiving module 901 is further configured to receive a fourth packet of the first service sent by the sending end, where the fourth packet carries a third sending timestamp, and the third sending timestamp corresponds to the time domain of the sending end, The time of sending the fourth message; the processing module 902 is also used to compare the size of the first sending time stamp and the third sending time stamp to determine whether the ordering of the first message is correct; the processing module 902 is also used for if the first If the packets are sorted incorrectly, adjust the first delay parameter.

Wherein, all relevant content of each step involved in the above-mentioned method embodiment can be referred to the function description of the corresponding function module, and will not be repeated here.

In this embodiment, the communication device 90 is presented in the form of dividing various functional modules in an integrated manner. A "module" here may refer to a specific ASIC, a circuit, a processor and a memory executing one or more software or firmware programs, an integrated logic circuit, and/or other devices that can provide the functions described above. In a simple embodiment, those skilled in the art can imagine that the communication device 90 can take the form of the communication device 50 shown in FIG. 5 .

For example, the processor 501 in the communication device 50 shown in FIG. 5 can invoke the computer-executed instructions stored in the memory 503, so that the communication device 50 executes the method for transmitting a message in the above method embodiment.

Specifically, the functions/implementation process of the receiving module 901 and the processing module 902 in FIG. 9 can be implemented by the processor 501 in the communication device 50 shown in FIG. 5 invoking computer-executed instructions stored in the memory 503 . Alternatively, the function/implementation process of the processing module 902 in FIG. 9 can be implemented by calling the computer execution instructions stored in the memory 503 by the processor 501 in the communication device 50 shown in FIG. /The implementation process can be implemented through the communication interface 504 in the communication device 50 shown in FIG. 5 .

Since the communication device 90 provided in this embodiment can execute the above-mentioned method for transmitting a message, the technical effect it can obtain can refer to the above-mentioned method embodiment, and details are not repeated here.

It should be noted that one or more of the above modules or units may be implemented by software, hardware or a combination of both. When any of the above modules or units is implemented by software, the software exists in the form of computer program instructions and is stored in the memory, and the processor can be used to execute the program instructions and realize the above method flow. The processor can be built into a SoC (system on a chip) or ASIC, or it can be an independent semiconductor chip. The core of the processor is used to execute software instructions for calculation or processing, and can further include necessary hardware accelerators, such as field programmable gate array (field programmable gate array, FPGA), PLD (programmable logic device) , or a logic circuit that implements a dedicated logic operation.

When the above modules or units are implemented by hardware, the hardware can be CPU, microprocessor, digital signal processing (digital signal processing, DSP) chip, microcontroller unit (microcontroller unit, MCU), artificial intelligence processor, ASIC, Any one or any combination of SoC, FPGA, PLD, dedicated digital circuit, hardware accelerator or non-integrated discrete device, which can run necessary software or not depend on software to execute the above method flow.

Optionally, an embodiment of the present application further provides a chip system, including: at least one processor and an interface, the at least one processor is coupled to the memory through the interface, and when the at least one processor executes the computer program or instruction in the memory When, the method in any one of the above method embodiments is executed. In a possible implementation manner, the communication device further includes a memory. Optionally, the system-on-a-chip may consist of a chip, or may include a chip and other discrete devices, which is not specifically limited in this embodiment of the present application.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server, or data center Transmission to another website site, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or may be a data storage device including one or more servers, data centers, etc. that can be integrated with the medium. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (solid state disk, SSD)), etc.

Although the present application has been described in conjunction with various embodiments here, however, in the process of implementing the claimed application, those skilled in the art can understand and Other variations of the disclosed embodiments are implemented. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that these measures cannot be combined to advantage.

Although the application has been described in conjunction with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely illustrative of the application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of this application. Obviously, those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. In this way, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

A method for transmitting messages, applied to a receiving end, characterized in that the method includes:

receiving the first packet of the first service sent by the sending end through the first path, the first packet carrying a first sending timestamp, the first sending timestamp corresponding to the time domain of the sending end, sending The time of the first message, the first path is one of multiple paths for transmitting the message of the first service to the receiving end;

Obtain a first delay parameter of the first service, where the first delay parameter is determined according to the first maximum transmission delay of the multiple paths;

Obtain a first expected read time according to the first sending timestamp and the first delay parameter;

Read the data of the first message according to the first estimated read time.
The method according to claim 1, wherein reading the data of the first message according to the first expected reading time comprises:

In multiple queues sorted by time, enqueue the first message according to the first expected reading time;

When the first expected reading time has been reached or exceeded, and the multiple queues indicate that it is time to read the data of the first message, the data of the first message is read.
The method according to claim 2, wherein the multiple queues include a first queue, and enqueuing the first message according to the first expected reading time includes:

Input the information of the first message into the first queue according to the difference between the first predicted reading time and the current time, and the difference between the first predicted reading time and the current time belongs to the first queue. The time difference interval corresponding to a queue.
The method according to claim 3, wherein information of the second message is also stored in the first queue,

If the first expected reading time is earlier than the expected reading time of the second message, the time when the information of the first message is output from the first queue is earlier than the second message The time at which the information was output from the first queue; or,

If the first expected reading time is later than the expected reading time of the second message, the time when the information of the first message is output from the first queue is later than that of the second message The time the message was output from the first queue.
The method according to claim 4, wherein the second message is other messages of the first service other than the first message sent by the sending end, and the second message sent by the sending end Messages of other services, or messages sent by other senders.
The method according to any one of claims 3-5, wherein the method further comprises:

If the difference between the first expected reading time and the current time is smaller than the minimum value of the time difference interval corresponding to the first queue, output the information of the first message from the first queue, input to the second queue, the second queue is included in the plurality of queues, and the difference between the first expected reading time and the current time belongs to the time difference interval corresponding to the second queue.
The method according to claim 6, wherein the plurality of queues are divided into multiple groups, the first queue is included in the first group of queues, and the second queue is included in the second group of queues , the length of the time difference interval corresponding to the queues in the first group of queues is greater than the length of the time difference interval corresponding to the queues in the second group of queues.
The method according to any one of claims 1-7, wherein the obtaining the first estimated read time according to the first sending timestamp and the first delay parameter comprises:

mapping the first sending timestamp to the time domain of the receiving end to obtain a second sending timestamp;

Obtain the first expected read time according to the second sending timestamp and the first delay parameter.
The method according to claim 8, characterized in that the method further comprises:

Obtain a first reference time stamp, a second reference time stamp and a first clock mapping parameter, the first reference time stamp is the time corresponding to the first moment in the time domain of the sending end, and the second reference time stamp is the time corresponding to the first moment in the time domain of the receiving end;

The mapping of the first sending timestamp to the time domain of the receiving end to obtain the second sending timestamp includes:

Obtain the second sending time stamp according to the first sending time stamp, the first reference time stamp, the second reference time stamp and the first clock mapping parameter.
The method according to claim 9, wherein the first moment corresponds to the time when the sending end sends the third message of the first service to the receiving end through the first path, so The method also includes:

Adjust the first clock mapping parameter according to the first transmission delay, the second transmission delay and the adjustment factor, where the first transmission delay is the transmission time of the first message from the sending end to the receiving end Transmission delay, the second transmission delay is the transmission delay of the third packet from the sending end to the receiving end.
The method according to any one of claims 1-10, further comprising:

receiving the fourth packet of the first service sent by the sending end, the fourth packet carrying a third sending timestamp, the third sending timestamp corresponding to the time domain of the sending end, sending the time of the fourth message;

Comparing the sizes of the first sending timestamp and the third sending timestamp to determine whether the sorting of the first message is correct;

If the sequence of the first packet is wrong, adjust the first delay parameter.
A communication device, characterized in that the communication device includes: a receiving module and a processing module;

The receiving module is configured to receive the first message of the first service sent by the sending end through the first path, the first message carries a first sending timestamp, and the first sending timestamp corresponds to the In the time domain of the sending end, the time when the first message is sent, and the first path is one of multiple paths for transmitting the message of the first service to the receiving end;

The processing module is configured to obtain a first delay parameter of the first service, where the first delay parameter is determined according to the first maximum transmission delay of the multiple paths;

The processing module is further configured to obtain a first expected read time according to the first sending timestamp and the first delay parameter;

The processing module is further configured to read the data of the first message according to the first expected reading time.
The communication device according to claim 12, wherein:

The processing module is specifically configured to enqueue the first message according to the first expected reading time in multiple queues sorted by time;

The processing module is further specifically configured to read the first message when the first expected reading time has been reached or exceeded, and the multiple queues indicate that it is time to read the data of the first message. The data of the first message.
The communication device according to claim 13, wherein:

The processing module is further specifically configured to input the information of the first message into the first queue according to the difference between the first expected reading time and the current time, and the first expected reading time and The current time difference belongs to the time difference interval corresponding to the first queue.
The communication device according to claim 14, wherein information of the second message is also stored in the first queue,

If the first expected reading time is earlier than the expected reading time of the second message, the time when the information of the first message is output from the first queue is earlier than the second message The time at which the information was output from the first queue; or,

If the first expected reading time is later than the expected reading time of the second message, the time when the information of the first message is output from the first queue is later than that of the second message The time the message was output from the first queue.
The communication device according to claim 15, wherein the second message is other messages of the first service other than the first message sent by the sending end, and the sending end sends Messages of other services, or messages sent by other senders.
The communication device according to any one of claims 14-16, characterized in that,

The processing module is further configured to: if the difference between the first expected read time and the current time is smaller than the minimum value of the time difference interval corresponding to the first queue, then send the information of the first message to Output from the first queue, input to the second queue, the second queue is included in the plurality of queues, the difference between the first expected read time and the current time belongs to the corresponding to the second queue Time difference interval.
The communication device according to claim 17, wherein the multiple queues are divided into multiple groups, the first queue is included in the first group of queues, and the second queue is included in the second group of queues wherein, the length of the time difference interval corresponding to the queues in the first group of queues is greater than the length of the time difference interval corresponding to the queues in the second group of queues.
The communication device according to any one of claims 12-18, characterized in that,

The processing module is specifically configured to map the first sending timestamp to the time domain of the receiving end to obtain a second sending timestamp;

The processing module is further specifically configured to obtain the first expected read time according to the second sending timestamp and the first delay parameter.
The communication device according to claim 19, wherein:

The processing module is further configured to obtain a first reference time stamp, a second reference time stamp and a first clock mapping parameter, the first reference time stamp is the time corresponding to the first moment in the time domain of the sending end , the second reference time stamp is the time corresponding to the first moment in the time domain of the receiving end;

The processing module is further specifically configured to obtain the second sending time stamp according to the first sending time stamp, the first reference time stamp, the second reference time stamp and the first clock mapping parameter .
The communication device according to claim 20, wherein the first moment corresponds to the time when the sending end sends the third message of the first service to the receiving end through the first path,

The processing module is further configured to adjust the first clock mapping parameter according to the first transmission delay, the second transmission delay and an adjustment factor, the first transmission delay being the The transmission delay from the sending end to the receiving end, and the second transmission delay is the transmission delay of the third packet from the sending end to the receiving end.
The communication device according to any one of claims 12-21, characterized in that,

The receiving module is further configured to receive a fourth message of the first service sent by the sending end, where the fourth message carries a third sending timestamp, and the third sending timestamp corresponds to the In the time domain of the sending end, the time for sending the fourth message;

The processing module is further configured to compare the sizes of the first sending time stamp and the third sending time stamp, and determine whether the sorting of the first message is correct;

The processing module is further configured to adjust the first delay parameter if the first packet is wrongly sorted.
A communication device, characterized in that it includes: a processor, the processor is coupled with a memory, and the memory is used to store a program or an instruction, and when the program or instruction is executed by the processor, the device Carrying out the method according to any one of claims 1 to 11.
A computer-readable medium, on which computer programs or instructions are stored, wherein when the computer program or instructions are executed, the computer executes the method according to any one of claims 1 to 11.
A communication system, characterized in that it includes: a sending end and a receiving end;

The sending end is configured to insert the first sending time stamp into the first message of the first service, and send the first message to the receiving end through the first path, and the first sending time stamp corresponds to In the time domain of the sending end, the time at which the first message is sent, the first path is one of multiple paths for transmitting the message of the first service to the receiving end;

The receiving end is configured to execute the method according to any one of claims 1-11.