CN114125931A

CN114125931A - Flow regulation method and device and network equipment

Info

Publication number: CN114125931A
Application number: CN202010896202.4A
Authority: CN
Inventors: 刘文杰; 刘大伟; 程亮; 党娟娜; 闫瑞栋
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-08-31
Filing date: 2020-08-31
Publication date: 2022-03-01

Abstract

The embodiment of the application discloses a flow regulation method, a device and a network device, wherein a source network node respectively sends a first message to a target network node through a plurality of communication paths so as to obtain path information corresponding to the network nodes on the plurality of communication paths, receives a second message which is returned by the target network node and summarizes the path information, and regulates the flow of at least one communication path in the plurality of communication paths according to the second message, because the second message received by the source network node comprises the path information of the network nodes between the source network node and the target network node and passed by all the communication paths, the flow can be globally regulated according to the overall condition of all the communication paths, the load imbalance caused by the overlapping of far-end links is avoided, and the problem of flow path congestion is solved, the flow balance effect is improved, and the network delay is reduced.

Description

Flow regulation method and device and network equipment

Technical Field

The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for adjusting traffic, and a network device.

Background

With the maturity of 5G networks and the popularization of emerging applications, metropolitan area networks have become the bottleneck of the whole network. When a large burst flow arrives, if the flow cannot be scheduled in time, the communication path congestion will be caused, the throughput of the network will be seriously affected, and the network delay with larger degree and longer duration time is caused.

In the prior art, the traffic of the metropolitan area network is distributed to different traffic paths through some load balancing algorithms, so as to improve the throughput of the metropolitan area network. For example, an Equal-Cost Multi-Path routing (ECMP) algorithm and an Unequal-Cost Multi-Path routing (UCMP) algorithm implement load balancing by finding other optimal paths between a source network node and a destination network node and distributing data streams arriving at the network nodes to the paths evenly.

However, the load balancing algorithm in the prior art only adjusts according to the load condition of the network device at the near end, and for a complex network communication path, the traffic balancing effect is poor, which causes the problems of communication path congestion and network delay increase.

Disclosure of Invention

The application provides a traffic regulation method, a traffic regulation device and network equipment, which aim to solve the problems of traffic path congestion and network delay increase.

In a first aspect, the present application provides a traffic adjusting method, applied to a source network node, including:

respectively sending a first message to a target network node through a plurality of communication paths, wherein the first message is used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information; receiving a second message from the target network node; the second message comprises path information corresponding to network nodes on a plurality of communication paths, or the second message is used for indicating flow regulation information; and according to the second message, carrying out flow regulation on at least one communication path in the plurality of communication paths.

In the application, a source network node sends first messages to a target network node through a plurality of communication paths respectively, so that path information corresponding to the network node on the plurality of communication paths is obtained, a second message which is returned by the target network node and summarizes the path information is received, and flow regulation is performed on at least one communication path in the plurality of communication paths according to the second message.

In one possible implementation, the communication path includes at least one link, and the path information is used to indicate a load of the link on which the network node is located.

Optionally, the path information includes at least one of: identification of the communication path, message sending timestamp, link bandwidth, link traffic, link utilization, input traffic of the communication path, and queue depth of the communication path.

In the application, the load of the link where the network node is located is indicated through the path information, the evaluation of the load condition of each link on the communication path is realized, the loads of all communication links are considered globally according to the load condition of each link, the load balance among different communication links is realized, and the effect of flow balance adjustment is improved.

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on a plurality of communication paths, performing flow adjustment on at least one communication path in the plurality of communication paths according to the second packet, includes: determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and performing traffic regulation on at least one communication path in the plurality of communication paths according to the traffic regulation information of each communication path.

In the application, the fair bandwidth of the communication paths is determined through the second message, and the target distribution flow is distributed to each communication path according to the fair bandwidth, so that the flow regulation of the plurality of communication paths is realized. Because the fair bandwidth of the communication path is determined according to the load condition of each link on each communication path, the target distribution flow of each communication path is determined according to the fair bandwidth, the flow of each communication path can be matched with the load condition, the effective flow balance is further realized, and the flow regulation effect is improved.

In a possible implementation manner, determining a fair bandwidth of a communication path according to path information corresponding to a network node of the communication path includes: determining a key link of the communication path according to path information corresponding to the network node of the communication path; the critical link of the communication path determines the load of the communication path; determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path to the link traffic of the key link; and determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the key link.

In the application, a key link of a communication path is determined through path information corresponding to a network node of the communication path, and the key link can determine a load of the communication path, namely a bottleneck link. The bandwidth utilization of the critical link is generally the highest, and therefore, in a communication path, the critical link is an important factor determining the traffic transmission performance of the communication path. According to the ratio of the input flow of the communication path to the link flow of the key link, namely the actual flow ratio of the flow of the communication path when passing through the key link, the fair bandwidth of the communication path can be further determined according to the flow ratio, the purpose of matching the fair bandwidth of the communication path with the load is achieved, the accuracy of the fair bandwidth is improved, and the adjusting effect of flow balance is improved.

In a possible implementation manner, after determining the fair bandwidth of the communication path according to a product of a traffic ratio of the communication path and a link bandwidth of the critical link, the method further includes: acquiring the queue depth of the communication path, wherein the queue depth is used for representing the time delay of the communication path, and the larger the queue depth is, the larger the time delay is; and correcting the fair bandwidth of the communication path according to the queue depth of the communication path.

Optionally, modifying the fair bandwidth of the communication path according to the queue depth of the communication path includes: determining a correction bandwidth according to a queue depth of a communication path, wherein the queue depth is in direct proportion to the correction bandwidth; and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth.

In this application, the queue depth is information for characterizing the size of the delay of the communication path, and when the queue depth on the communication path is larger, the delay is larger. In practical applications, as the depth of the queue of the communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic, i.e. affects the bandwidth of the communication path. Therefore, according to the queue depth, the correction bandwidth proportional to the queue depth is determined, and the correction bandwidth is subtracted from the fair bandwidth of the communication path to correct the fair bandwidth of the communication path.

In one possible implementation manner, the determining traffic adjustment information of each communication path according to the incoming traffic of each communication path and the fair bandwidth of each communication path includes: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; and determining the target utilization rate according to the ratio of the sum of the input flow of each communication path to the sum of the fair bandwidth of each communication path. And determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

In a possible implementation manner, the second packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the method further includes: determining a flow correction value according to the queue depth; and adjusting the flow of the plurality of communication paths according to the flow correction value.

In the application, the traffic of the plurality of communication paths is adjusted by obtaining the queue depth in the second message, wherein the queue depth is information for representing the time delay size of the communication path, and when the queue depth on the communication path is larger, the time delay is larger. In practical applications, as the depth of the queue of the communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic, i.e. affects the bandwidth of the communication path. Therefore, the flow of each communication path is regulated according to the depth of the queue, and the flow of the communication path with larger queuing depth is properly regulated to reduce the delay caused by queuing; for a communication path with a small queuing depth, the flow is properly regulated, and the flow transmission efficiency is improved.

In a second aspect, the present application provides a traffic adjusting method, applied to a target network node, including:

receiving first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information; generating second messages according to the first messages respectively corresponding to the plurality of communication paths; the second message comprises path information corresponding to network nodes on a plurality of communication paths, or the second message is used for indicating flow regulation information; and sending the second message to the source network node.

In the application, the target network node receives first messages respectively sent by the source network node through a plurality of communication paths, so that path information corresponding to the network node on the plurality of communication paths is obtained, after the path information is summarized, a second message is generated and sent to the source network node, and the source network node can adjust the flow according to the second message. The second message sent to the source network node contains the path information of the network nodes which are between the source network node and the target network node and through which all communication paths pass, so that the flow can be globally adjusted according to the overall situation of all communication paths, load imbalance caused by overlapping of far-end links is avoided, the problem of traffic path congestion is solved, the flow balancing effect is improved, and network delay is reduced.

In a possible implementation manner, when the second packet is used to indicate the flow adjustment information, generating the second packet according to the first packets respectively corresponding to the plurality of communication paths includes: determining path information corresponding to network nodes of each communication path according to first messages respectively corresponding to the plurality of communication paths; determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and generating a second message according to the flow regulation information of each communication path.

In one possible implementation manner, the determining traffic adjustment information of each communication path according to the incoming traffic of each communication path and the fair bandwidth of each communication path includes: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; determining a target utilization rate according to the ratio of the sum of the input flows of all the communication paths to the sum of the fair bandwidths of all the communication paths; and determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

In a possible implementation manner, the generating the second packet according to the traffic adjustment information of each communication path includes:

determining the target regulation flow of each communication path according to the difference value between the target distribution flow of each communication path and the input flow of each communication path, and packaging the target regulation flow into a second message, or; and encapsulating the target distribution flow of each communication path into a second message.

In the method, the target network node acquires path information corresponding to the network nodes on the plurality of communication paths through the first message, determines flow regulation information matched with the load of each communication path, packages the flow regulation information into the second message in a plurality of ways, and sends the second message to the source network node, so that the source network node can perform flow balance regulation on the communication paths. Because the flow regulation information is determined to be executed on one side of the target network node, after the source target network node receives the flow regulation information, the flow regulation can be directly carried out on the communication path according to the flow regulation information, extra calculation is not needed, the calculation load of the source network node is reduced, and the overall efficiency of the flow regulation process is improved.

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on a plurality of communication paths, generating the second packet according to the first packets respectively corresponding to the plurality of communication paths includes: and encapsulating the path information in the first message corresponding to the plurality of communication paths into a second message.

In the method and the device, after the target network node receives the first message, the path information corresponding to the network node is collected and then returned to the source network node for processing, so that the data processing time is saved, the source network node can obtain all the path information from the source network node to the target network node more quickly, and the real-time performance of the source network node in adjusting the communication path is improved.

In a possible implementation manner, the first packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the method further includes: determining a flow correction value according to the queue depth; and the flow correction value is arranged in the second message.

In the application, the queue depth is information for representing the size of the delay of the communication path, and when the queue depth on the communication path is larger, the delay is larger, and in practical application, when the queue depth of the communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic. The target network node sets the paired depth in the second message and sends the second message to the source network node, so that the source network node can obtain queue depth information corresponding to the communication path, and adjusts the flow of each communication path according to the queue depth information, thereby improving the accuracy and effect of flow balance.

In a third aspect, the present application provides a traffic adjusting apparatus, applied to a source network node, the apparatus including a transceiver module and a processing module, wherein:

the system comprises a receiving and sending module, a flow regulating module and a sending and receiving module, wherein the receiving and sending module is used for respectively sending a first message to a target network node through a plurality of communication paths, the first message is used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining the flow regulating information; receiving a second message from the target network node; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information.

And the processing module is used for carrying out flow regulation on at least one communication path in the plurality of communication paths according to the second message.

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on multiple communication paths, the processing module is specifically configured to: determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and performing traffic regulation on at least one communication path in the plurality of communication paths according to the traffic regulation information of each communication path.

In a possible implementation manner, when determining the fair bandwidth of the communication path according to the path information corresponding to the network node of the communication path, the processing module is specifically configured to: determining a key link of the communication path according to path information corresponding to the network node of the communication path; the critical link of the communication path determines the load of the communication path; determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path to the link traffic of the key link; and determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the key link.

In a possible implementation manner, after determining the fair bandwidth of the communication path according to a product of a traffic ratio of the communication path and a link bandwidth of the key link, the processing module is specifically configured to: acquiring the queue depth of the communication path, wherein the queue depth is used for representing the time delay of the communication path, and the larger the queue depth is, the larger the time delay is; and correcting the fair bandwidth of the communication path according to the queue depth of the communication path.

Optionally, when the processing module corrects the fair bandwidth of the communication path according to the queue depth of the communication path, the processing module is specifically configured to: determining a correction bandwidth according to a queue depth of a communication path, wherein the queue depth is in direct proportion to the correction bandwidth; and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic, and when determining the traffic adjustment information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path, the processing module is specifically configured to: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; and determining the target utilization rate according to the ratio of the sum of the input flow of each communication path to the sum of the fair bandwidth of each communication path. And determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

In a possible implementation manner, the second packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the processing module is further configured to: determining a flow correction value according to the queue depth; and adjusting the flow of the plurality of communication paths according to the flow correction value.

In a fourth aspect, the present application provides a traffic regulation apparatus applied to a target network node, the apparatus includes a transceiver module and a processing module, wherein:

the receiving and sending module is used for receiving first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

The processing module is used for generating second messages according to the first messages respectively corresponding to the plurality of communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information.

And the transceiver module is also used for sending the second message to the source network node.

In a possible implementation manner, when the second packet is used to indicate the flow adjustment information, the processing module is specifically configured to: determining path information corresponding to network nodes of each communication path according to first messages respectively corresponding to the plurality of communication paths; determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and generating a second message according to the flow regulation information of each communication path.

In this application, the queue depth is information for characterizing the size of the delay of the communication path, and the greater the depth on the communication path is, the greater the delay is. In practical applications, as the depth of the queue of the communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic, i.e. affects the bandwidth of the communication path. Therefore, according to the queue depth, the correction bandwidth proportional to the queue depth is determined, and the correction bandwidth is subtracted from the fair bandwidth of the communication path to correct the fair bandwidth of the communication path.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic, and when determining the traffic adjustment information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path, the processing module is specifically configured to: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; determining a target utilization rate according to the ratio of the sum of the input flows of all the communication paths to the sum of the fair bandwidths of all the communication paths; and determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic or a target adjustment traffic, and when the processing module generates the second packet according to the traffic adjustment information of each communication path, the processing module is specifically configured to:

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on multiple communication paths, the processing module is specifically configured to: and encapsulating the path information in the first message corresponding to the plurality of communication paths into a second message.

In a possible implementation manner, the first packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the processing module is further configured to: determining a flow correction value according to the queue depth; and the flow correction value is arranged in the second message.

In a fifth aspect, an embodiment of the present application provides a network device, including: a processor, a memory, and a transceiver;

the processor is used for controlling the transceiver to transmit and receive signals; the memory is used for storing a computer program; the processor is further configured to invoke and execute the computer program stored in the memory, so that the network device performs the method provided in any implementation manner of the first aspect above.

In a sixth aspect, an embodiment of the present application provides a network device, including: a processor, a memory, and a transceiver;

the processor is used for controlling the transceiver to transmit and receive signals; the memory is used for storing a computer program; the processor is further configured to call and execute the computer program stored in the memory, so that the network device performs the method provided in any implementation manner of the second aspect above.

In a seventh aspect, embodiments of the present application provide a computer-readable storage medium, which includes computer code, when executed on a computer, causes the computer to perform the method provided in any implementation manner of the first aspect or the second method.

In an eighth aspect, the present application provides a computer program product, which includes program code for performing the method provided in any implementation manner of the first aspect or the second method above when the computer runs the computer program product.

In a ninth aspect, the present application further provides a chip comprising a processor. The processor is configured to call and execute a computer program stored in the memory to perform corresponding operations and/or procedures performed by the source network node in the traffic regulation method provided in the embodiment of the present application. Optionally, the chip further comprises a memory, the memory is connected with the processor through a circuit or a wire, and the processor is used for reading and executing the computer program in the memory. Further optionally, the chip further comprises a communication interface, and the processor is connected to the communication interface. The communication interface is used for receiving data and/or information needing to be processed, and the processor acquires the data and/or information from the communication interface and processes the data and/or information. The communication interface may be an input output interface.

In a tenth aspect, the present application further provides a chip including a processor. The processor is configured to call and execute a computer program stored in the memory to perform corresponding operations and/or procedures performed by the target network node in the traffic regulation method provided in the embodiment of the present application. Optionally, the chip further comprises a memory, the memory is connected with the processor through a circuit or a wire, and the processor is used for reading and executing the computer program in the memory. Further optionally, the chip further comprises a communication interface, and the processor is connected to the communication interface. The communication interface is used for receiving data and/or information needing to be processed, and the processor acquires the data and/or information from the communication interface and processes the data and/or information. The communication interface may be an input output interface.

Drawings

Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;

FIG. 2 is a diagram illustrating traffic balancing for multiple communication paths in the prior art;

fig. 3 is a schematic flow chart of a flow rate adjustment method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a communication path within a metropolitan area network;

fig. 5 is a schematic flow chart of another flow rate adjustment method provided in the embodiment of the present application;

fig. 6 is a schematic diagram of a link overlap according to an embodiment of the present application;

FIG. 7 is a flowchart of one implementation of step S203 in the embodiment shown in FIG. 5;

fig. 8 is a schematic diagram of link traffic of a key link according to an embodiment of the present disclosure;

FIG. 9 is a flowchart of one implementation of step S204 in the embodiment shown in FIG. 5;

fig. 10 is a schematic flow chart of another flow rate adjustment method provided in the embodiment of the present application;

fig. 11 is a schematic flow chart of a flow rate adjustment method according to an embodiment of the present application;

fig. 12 is a signaling diagram of a traffic regulating method according to an embodiment of the present application;

fig. 13 is a schematic flow chart of another flow rate adjustment method provided in the embodiment of the present application;

fig. 14 is a signaling diagram of a traffic regulating method according to an embodiment of the present application;

fig. 15 is a signaling diagram of a traffic regulating method according to an embodiment of the present application;

FIG. 16 is a schematic block diagram of a flow regulating device provided by an embodiment of the present application;

FIG. 17 is a schematic block diagram of a flow regulating device provided in an embodiment of the present application;

fig. 18 is a schematic block diagram of a network device according to an embodiment of the present application;

fig. 19 is a schematic block diagram of a network device according to an embodiment of the present application;

fig. 20 is a schematic block diagram of another network device provided in an embodiment of the present application;

fig. 21 is a schematic block diagram of another network device according to an embodiment of the present disclosure.

Detailed Description

The embodiment of the present application may be applied to a fifth-generation mobile communication network (5th-generation, 5G) communication system or other systems that may appear in the future, and may also be applied to other communication systems, for example: wireless Local Area Network (WLAN) system, global system for mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD), universal mobile telecommunications system (universal mobile telecommunications system, UMTS), Worldwide Interoperability for Microwave Access (WiMAX) system, and the like.

Some terms in the present application are explained below to facilitate understanding by those skilled in the art. It should be noted that, when the scheme of the embodiment of the present application is applied to a 5G system, an existing system, or another system that may appear in the future, names of network devices may change, but this does not affect the implementation of the scheme of the embodiment of the present application.

1) Metropolitan Area Networks (MAN) refer to computer communication networks established within a city. The metropolitan area network is a typical application of a broadband metropolitan area network, which is a local integrated service network that uses a broadband Transmission network as an open platform, uses a Transmission Control Protocol/Internet Protocol (TCP/IP) as a basis, and realizes voice, digital, image, multimedia video, IP telephone, IP access and various value-added service industries and intelligent services through various network interconnection equipment, and is interconnected and intercommunicated with a wide area computer network, a broadcast television network and a telephone switching network. The metropolitan area network comprises an urban backbone network and an urban access network, wherein the urban backbone network is used for being connected with other backbone networks, and the urban access network is used for connecting network access users with the urban backbone network.

2) A terminal device, also called a terminal or a user device, is a device for providing voice and/or data connectivity to a user, for example, a handheld device with a wireless connection function, a vehicle-mounted device, and the like; the terminal device may also be a device that detects data, e.g., a sensor, etc.; the terminal device may also be a smart device, for example, a smart home device, a wearable device, etc. deployed indoors. Common terminal devices include, for example: air quality monitoring sensor, temperature sensor, smoke transducer, cell-phone, panel computer, notebook computer, palm computer, Mobile Internet Device (MID), wearable equipment, wherein, wearable equipment for example includes: smart watches, smart bracelets, pedometers, and the like. The terminal equipment is terminal equipment for wireless communication or terminal equipment for limited communication which is possible now and in the future.

3) A network device, also called a Radio Access Network (RAN) device, is a device for accessing a terminal device to a wireless network, and includes devices in various communication systems, for example, the network device includes but is not limited to: a transmission point (TRP), a base station (e.g., gNB), a Radio Network Controller (RNC), a Node B (NB), a Base Station Controller (BSC), a bts (base transceiver station), a henb (home evolved nodeb), or an hnb (home Node B), a Base Band Unit (BBU), etc.

4) "plurality" means two or more, and other terms are analogous. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

5) "correspond" may refer to an association or binding relationship, and a corresponds to B refers to an association or binding relationship between a and B.

It should be noted that the terms or terms referred to in the embodiments of the present application may be mutually referred and are not described in detail.

Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application, and as shown in fig. 1, a network user accesses a metropolitan area network through a terminal device and accesses the internet through the metropolitan area network. The flow passing through the metropolitan area network reaches the terminal equipment through the inlet network node and the outlet network node, and the transmission of the network flow is completed. Wherein the content of the first and second substances,

with the maturity of 5G networks and the popularization of emerging applications, metropolitan area networks have become the bottleneck of the whole network. When the burst large flow arrives, if the flow cannot be scheduled in time, the link congestion will be caused, the throughput of the network is seriously influenced, and the time delay of the network is large and is not easy to reduce rapidly. In practical applications, the links of the network part are overloaded or even overloaded, for example, the utilization rate of the device interfaces on the links is above 30%, even above 80%. In this state, traffic is likely to be congested or even lost, and meanwhile, a large number of links on the network are in a light load state, that is, the utilization rate of an interface is lower than 30%, even a few percent, which causes imbalance of traffic on each path.

In the prior art, through some load balancing algorithms, the metro network traffic can be distributed to different traffic paths, so as to improve the throughput of the metro network. For example, the ECMP algorithm and the UCMP algorithm, find other optimal paths between the source network node and the destination network node, and evenly distribute the data streams of the arriving network nodes to the paths, so as to achieve load balancing. However, in practical applications, because the conditions of bandwidth, delay, reliability and the like of each communication path are inconsistent, the flow equalization is simply performed through a Hash algorithm or a bandwidth ratio, and the effect is poor. Fig. 2 is a schematic diagram of traffic balancing for multiple communication paths in the prior art, and as shown in fig. 2, a source network node receiving traffic on a communication path only performs traffic balancing according to a load condition on a near-end path connected to the source network node, but does not consider whether traffic is superimposed on a far-end path, and finally determines communication quality on the communication path, which is bandwidth utilization of a bottleneck link on the communication path. Therefore, when a bottleneck link on the communication path appears in a remote path due to traffic superposition and other reasons, a source network node for load traffic balance adjustment cannot obtain link information of the bottleneck link, and therefore corresponding traffic regulation cannot be performed on the bottleneck link, so that traffic congestion occurs on the bottleneck link, and delay and communication quality of the whole communication path are reduced.

In order to solve the problems of network delay increase and communication quality reduction caused by congestion of the communication paths, embodiments of the present application provide a flow adjustment method, an apparatus, and a network device, where a plurality of communication paths respectively send first packets to a target network node, so as to obtain path information corresponding to the network node on the plurality of communication paths, receive a second packet, which is returned by the target network node and summarizes the path information, and perform flow adjustment on at least one communication path in the plurality of communication paths according to the second packet, so as to solve the problem of congestion of the flow path, improve the flow balancing effect, and reduce network delay.

Fig. 3 is a schematic flow chart of a traffic regulation method provided in an embodiment of the present application, where an execution subject of the method may be a source network node, as shown in fig. 3, the method includes:

s101, respectively sending first messages to a target network node through a plurality of communication paths, wherein the first messages are used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

For example, the source network node may be an ingress network node of a metropolitan area network, and external traffic enters the metropolitan area network from the source network node, and after passing through a plurality of intermediate network nodes, is transmitted from a target network node, that is, an egress network node, to complete a traffic transmission process. Fig. 4 is a schematic diagram of a communication path in a metropolitan area network, where as shown in fig. 4, a plurality of network nodes are connected downstream of a source network node, and the source network node is connected to different network nodes and finally connected to a target network node to form a plurality of different communication paths. And the source network node finally realizes the balance adjustment of the flow by controlling the flow distribution on different communication paths. The network node is a network device, and may be a network node device, such as a router, a switch, or a network endpoint device, such as a network card.

In a possible implementation manner, the first packet may be a measurement request packet that is sent by a source network node and includes request information, the source network node sends the measurement request packet to a plurality of communication paths, and when the measurement request packet passes through a network node in a communication path, the network node reports path information of a link where the network node is located to the measurement request packet, so that the measurement request packet can obtain path information corresponding to the network node. The source network node can send a first message to the target network node according to a preset fixed time interval so as to meet the requirement of periodic flow adjustment; the source network node can also dynamically send the first message to the target network node according to the specific network environment and network conditions, so as to realize more real-time flow regulation.

In one possible implementation, the communication path includes at least one link, and the path information is used to indicate a load of the link on which the network node is located. Illustratively, the path information includes at least one of: identification of the communication path, message sending timestamp, link bandwidth, link traffic, link utilization, input traffic of the communication path, and queue depth of the communication path. The ratio of the link traffic to the link bandwidth is the link utilization. The higher the link utilization, the more load pressure the link is under, i.e., the more congested the link is. Through the link utilization rate, the performance condition of the corresponding link can be expressed. Correspondingly, according to the path information, the flow regulation information can be determined, and the flow on the communication path with the larger load pressure is shunted to the communication path with the smaller load pressure, so that the load pressure among the communication paths is kept balanced.

In a possible implementation manner, the network node compares the link utilization of the located link with the existing link utilization in the first message, and stores the link with the greater link utilization in the first message. When the first message sequentially passes through each network node in the corresponding communication path to reach the target network node, the first message includes the maximum link utilization rate of each link section on the communication path, the link corresponding to the maximum link utilization rate is a bottleneck link, and the bottleneck link determines the performance of the communication path.

S102, receiving a second message from a target network node; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information.

Illustratively, the second packet is information sent by the target network node, and the second packet summarizes path information corresponding to all network nodes between the source network node and the target network node, so that according to the second packet, traffic adjustment on multiple communication paths can be realized, traffic on each communication path is kept balanced, and efficiency of flow transmission is improved.

In a possible implementation manner, the second packet may include path information corresponding to the original network node or the network node partially processed by the target network node. For example, the second message includes only the link utilization of the bottleneck link on each communication path. Of course, the link utilization of all links on each communication path and other path information may also be included, and may be set according to specific needs, which is not specifically limited herein.

In another possible implementation manner, the second packet is traffic adjustment information obtained after the target network node processes path information corresponding to the network node on each communication path. The source network device can directly adjust the flow according to the flow adjusting information, and the purpose of flow balance of each communication path is achieved.

S103, according to the second message, flow regulation is carried out on at least one communication path in the plurality of communication paths.

Exemplarily, after receiving the second message, if the second message includes path information corresponding to the network node on each communication path, the source network node needs to determine flow adjustment information according to the load condition of each link on each communication path represented by the path information, and adjust the flow of the communication path according to the flow adjustment information; and if the second message comprises the information for indicating the flow regulation information, regulating the flow of the communication path directly according to the information in the second message. The specific process of adjusting the traffic according to the traffic adjustment information is prior art in the field, and is not described herein again.

Fig. 5 is a schematic flow chart of another flow rate adjustment method provided in the embodiment of the present application, and as shown in fig. 5, the flow rate adjustment method provided in this embodiment further details step S103 on the basis of the flow rate adjustment method provided in the embodiment shown in fig. 3, and the method includes:

s201, sending first messages to a target network node through a plurality of communication paths respectively, wherein the first messages are used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

S202, receiving a second message from the target network node; the second message includes path information corresponding to network nodes on a plurality of communication paths.

S203, according to the path information corresponding to the network node of each communication path, determining the fair bandwidth of each communication path.

Exemplarily, during traffic transmission, a certain link may overlap in each communication path, and fig. 6 is a schematic diagram of a link overlap provided in the embodiment of the present application, as shown in fig. 6, a communication path a overlaps a communication path B at a link c, and a traffic of the communication path a and a traffic of the communication path B are merged at the link c, and in the case of the same bandwidth and the same traffic, a bandwidth utilization rate at the link c is 2 times that of other links of the communication path a and the communication path B. In this case, if the bandwidth of the overlapping link cannot meet the traffic transmission requirements of the multiple communication links, the bandwidth of the overlapping link, that is, the fair bandwidth, needs to be allocated according to the ratio of the actual traffic of the multiple communication paths.

Illustratively, as shown in fig. 7, in one possible implementation, S203 includes three specific implementation steps of S2031, S2032, and S2033:

s2031, determining a key link of the communication path according to the path information corresponding to the network node of the communication path; the critical links of the communication path determine the load of the communication path.

Illustratively, the path information may include: link bandwidth and link traffic, or path information may also include link utilization. The ratio of the link traffic to the link bandwidth is the link utilization. The higher the link utilization, the more load pressure the link is under, i.e., the more congested the link is. Through the link utilization rate, the performance condition of the corresponding link can be expressed. The link corresponding to the maximum link utilization rate is a critical link, that is, a bottleneck link determining the performance of the communication path.

S2032, determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path and the link traffic of the key link.

The input traffic of each communication path overlaps at the critical link, and thus, the link traffic of the critical link is the sum of the input traffic of each communication path passing through the critical link. Fig. 8 is a schematic diagram of link traffic of a critical link according to an embodiment of the present application, and as shown in fig. 8, an input traffic of a communication path a is 10, an input traffic of a communication path B is 20, the communication path a and the communication path B overlap in a critical link c, and a link traffic passing through the critical link c is 30. At this time, the traffic ratio of the communication path a is 1/3; the traffic ratio of the communication path B is 2/3.

S2033, according to the product of the flow rate of the communication path and the link bandwidth of the key link, determining the fair bandwidth of the communication path.

The path information also includes link bandwidths of the links. After the critical link is determined, the link bandwidth of the critical link can be correspondingly determined. The link bandwidth of a critical link is the maximum bandwidth that the critical link can provide and is also the maximum bandwidth of the corresponding communication path. Based on the product of the traffic fraction of the communication path and the link bandwidth of the key link, a fair bandwidth matching the actual load of each communication path through the key link can be determined separately.

In a possible implementation manner, after step S203, the method further includes:

and S203A, obtaining the queue depth of the communication path, wherein the queue depth is used for characterizing the time delay of the communication path.

Specifically, the queue depth is information for characterizing the size of the delay of the communication path, and the delay is larger when the queue depth on the communication path is larger. In practical applications, as the queue depth of a communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic, so that when the queue depth is too large, bandwidth of the communication path is affected.

S203B, the fair bandwidth of the communication path is corrected according to the queue depth of the communication path.

Exemplarily, specifically, the method comprises the following steps: determining a correction bandwidth according to a queue depth of a communication path, wherein the queue depth is in direct proportion to the correction bandwidth; and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth.

In one possible implementation manner, in order to eliminate the influence of the queue depth on the fair bandwidth, normalization processing is performed on the queue depth and the fair bandwidth, that is, the degree of influence of the queue depth on the fair bandwidth is determined, for example, when the queue depth is N, the corresponding correction bandwidth is M, and the corrected bandwidth is subtracted from the fair bandwidth to obtain the corrected fair bandwidth. The queue depth and the modified bandwidth M have a mapping relationship, and the mapping relationship may be preset in a network device or determined according to a specific network condition, and may be set according to the specific condition, which is not described in detail.

In the application, the fair bandwidth is corrected by obtaining the queuing depth corresponding to the communication path, and as the queuing depth of the communication path is larger, queuing delay is more likely to be generated, and the queuing delay affects throughput of network traffic, namely, affects the bandwidth of the communication path. Therefore, according to the queue depth, the correction bandwidth proportional to the queue depth is determined, and the correction bandwidth is subtracted from the fair bandwidth of the communication path to correct the fair bandwidth of the communication path.

And S204, determining the flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path.

Illustratively, as shown in fig. 9, in a possible implementation, the flow rate adjustment information includes a target distribution flow rate, and S204 includes three specific implementation steps S2041, S2042, and S2043:

s2041, acquiring the sum of the input flow of each communication path and the sum of the fair bandwidth of each communication path.

S2042, determining the target utilization rate according to the ratio of the sum of the input flows of the communication paths to the sum of the fair bandwidths of the communication paths.

Specifically, the sum of the input traffic of each communication path is the sum of the traffic of all communication paths passing through the source network node. The sum of the incoming traffic for each communication path may be obtained directly by the source network node. The sum of the fair bandwidths of the communication paths, i.e. the sum of the bandwidths actually occupied by all the communication paths, is also the sum of the link bandwidths of all the critical links. The sum of the input flow of each communication path is equivalent to the total load of all the communication paths input by the source network node; the sum of the fair bandwidths of the communication paths corresponds to the total bandwidth of all communication paths input via the source network node.

Further, the ratio of the sum of the input flows of each communication path to the sum of the fair bandwidths of each communication path is the average bandwidth utilization rate of all communication paths between the source network node and the target network node, and when the bandwidth utilization rate of each communication path reaches the average bandwidth utilization rate, the network reaches the optimal balance. Therefore, the average bandwidth utilization ratio is a target utilization ratio, and the traffic of each communication path is adjusted by the target utilization ratio, so that the optimal load balance can be realized.

S2043, determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

The fair bandwidth determined in the previous step is determined by the real load on each communication path, so that the fair bandwidth is matched with the input traffic of each communication path, and further, the product of the fair bandwidth of the communication path and the target utilization rate can determine the optimal traffic, i.e., the target allocation traffic, corresponding to each communication path. Each communication path performs traffic transmission according to the corresponding target allocation traffic, so that the bandwidth utilization rate of each communication path can reach the target utilization rate, that is, the load balancing effect is optimal.

S205, performing traffic regulation on at least one of the plurality of communication paths according to the traffic regulation information of each communication path.

After determining the target individual traffic of each communication path, the current traffic of each communication path may be adjusted, specifically, for example, a current traffic value of each communication path is obtained, a difference between the current traffic value and the target allocated traffic is calculated, and the call-in traffic or the call-out traffic of the communication path is performed according to the difference. Of course, it is understood that if the current flow value of a communication path is just the target allocated flow, no flow adjustment may be performed for that communication path.

In this embodiment, the implementation manners of S201 to S202 are the same as the implementation manners of S101 to S102 in the embodiment shown in fig. 3, and are not described again here.

Fig. 10 is a schematic flow chart of another flow rate adjustment method provided in an embodiment of the present application, and as shown in fig. 10, the flow rate adjustment method provided in this embodiment further details step S103 on the basis of the flow rate adjustment method provided in the embodiment shown in fig. 3, and the method includes:

s301, sending first messages to the target network node through the plurality of communication paths respectively, wherein the first messages are used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

S302, receiving a second message from a target network node; and the second message is used for indicating the flow regulation information.

S303, according to the second message, carrying out flow regulation on at least one communication path in the plurality of communication paths.

Illustratively, the second message includes traffic adjustment information, where the traffic adjustment information is information, such as parameters, data, and identifiers, obtained after the target network node processes path information corresponding to the network node on each communication path, and is used to adjust traffic of each communication path. The source network device can directly adjust the flow according to the flow adjusting information, and the purpose of flow balance of each communication path is achieved. The specific method according to the flow regulation information is the prior art in the field, and is not described herein again.

In this embodiment, the implementation manners of S301 to S302 are the same as the implementation manners of S101 to S102 in the embodiment shown in fig. 3, and are not described again here.

In the application, a source network node sends first messages to a target network node through a plurality of communication paths respectively, so that path information corresponding to the network node on the plurality of communication paths is obtained, a second message which is returned by the target network node and used for indicating flow regulation information is received, and flow regulation is performed on at least one communication path in the plurality of communication paths according to the second message. Because the flow regulation information is determined to be executed on one side of the target network node, after the source target network node receives the flow regulation information, the flow regulation can be directly carried out on the communication path according to the flow regulation information, extra calculation is not needed, the calculation load of the source network node is reduced, and the overall efficiency of the flow regulation process is improved.

Fig. 11 is a schematic flow chart of a traffic regulation method provided in an embodiment of the present application, where an execution subject of the method may be a target network node, as shown in fig. 11, the method includes:

s401, receiving first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

For example, the first packet may be a measurement request packet containing request information sent by a source network node, where the source network node sends the measurement request packet to multiple communication paths, and when the measurement request packet passes through a network node in a communication path, the network node may report path information of a link where the network node is located to the measurement request packet, so that the measurement request packet can obtain path information corresponding to the network node. The first message received by the target network message includes corresponding path information reported by the network node on the communication path.

S402, generating second messages according to the first messages respectively corresponding to the plurality of communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information.

In a possible implementation manner, after receiving the first message corresponding to each communication path, the target network device obtains path information corresponding to a network node in the first message, and encapsulates the original path information or the partially processed path information to form a second message. Specifically, for example, after the target network device processes the path information corresponding to the network node in the first message, the link utilization rate of the bottleneck link on the communication path is obtained, and the link utilization rate of the bottleneck link on the communication path is encapsulated into the second message. Of course, the link utilization rates of all links on each communication path and other path information may also be encapsulated into the second packet, which may be set according to specific needs, and is not specifically limited herein.

In another possible implementation manner, the second packet is traffic adjustment information obtained after the target network node processes path information corresponding to the network node on each communication path. After the target network node sends the second message to the source network device, the source network device can directly adjust the flow according to the flow adjustment information, so as to achieve the purpose of flow balance of each communication path.

S403, sending the second message to the source network node.

The target network node may return the second packet to the source network node through one or more communication paths, and the source network node may implement the flow adjustment on at least one communication path in the multiple communication paths according to the second packet, and the specific implementation steps may refer to the schemes corresponding to the embodiments shown in fig. 3 to fig. 10, which are not described herein again.

Fig. 12 is a signaling diagram of a traffic regulation method according to an embodiment of the present application, and as shown in fig. 12, the traffic regulation method according to the embodiment includes:

s501, the source network node sends first messages to the target network node through a plurality of communication paths respectively, wherein the first messages are used for acquiring path information corresponding to the network nodes on the communication paths, and the path information is used for determining flow regulation information.

S502, a target network node receives first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network nodes on the communication paths.

S503, the target network node generates a second message according to the first messages respectively corresponding to the plurality of communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information.

S504, the target network node sends a second message to the source network node.

And S505, the source network node receives the second message from the target network node.

S506, the source network node adjusts the flow of at least one communication path in the plurality of communication paths according to the second message.

In the embodiment of the application, a source network node sends first messages to a target network node through a plurality of communication paths respectively, so that path information corresponding to the network node on the plurality of communication paths is obtained, a second message which is returned by the target network node and summarizes the path information is received, and flow regulation is performed on at least one communication path in the plurality of communication paths according to the second message.

Fig. 13 is a schematic flow chart of another flow rate adjustment method provided in the embodiment of the present application, and as shown in fig. 13, the flow rate adjustment method provided in this embodiment further details step S402 on the basis of the flow rate adjustment method provided in the embodiment shown in fig. 11, and the method includes:

s601, receiving first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information.

S602, determining path information corresponding to the network node of each communication path according to the first messages respectively corresponding to the plurality of communication paths.

Specifically, each first packet corresponds to a communication path, and when the first packet passes through a network node on the communication path, path information corresponding to the network node is recorded, and the path information corresponding to one or more network nodes can be obtained by analyzing the first packet, where a specific implementation manner of analyzing the packet and obtaining the information therein is the prior art in the field, and is not described here again.

S603, determining fair bandwidth of each communication path according to the path information corresponding to the network node of each communication path.

Optionally, after step S603, the method further includes:

S603A, obtaining the queue depth of the communication path, wherein the queue depth is used for characterizing the time delay size of the communication path.

S603B corrects the fair bandwidth of the communication path according to the queue depth of the communication path.

And S604, determining the flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path.

And S605, generating a second message according to the flow regulation information of each communication path.

And the target network node processes the path information corresponding to the network node on each communication path to obtain flow regulation information, encapsulates the flow regulation information and generates a second message. After the target network node sends the second message to the source network device, the source network device can directly adjust the flow according to the flow adjustment information, so as to achieve the purpose of flow balance of each communication path.

S606, sending the second message to the source network node.

In this embodiment, the implementation manners of S601 and S606 are the same as the implementation manners of S401 and S403 in the embodiment shown in fig. 11 of this application, and the specific implementation manners and technical effects of the steps can be referred to the descriptions in the above embodiments, and are not described herein again. S603-S604 are processes for determining target adjustment information, which are the same as the implementation manners of steps S203-S204 in the flow rate adjustment method provided in the embodiments corresponding to fig. 5-9, and specific implementation manners and technical effects of the steps can be referred to the descriptions in the above embodiments, and are not described herein again.

Fig. 14 is a signaling diagram of a traffic regulation method according to an embodiment of the present application, and as shown in fig. 14, the traffic regulation method according to the embodiment includes:

s701, the source network node sends first messages to the target network node through a plurality of communication paths respectively, wherein the first messages are used for obtaining path information corresponding to the network nodes on the communication paths, and the path information is used for determining flow regulation information.

S702, a target network node receives first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network nodes on the communication paths.

S703, the target network node determines path information corresponding to the network node of each communication path according to the first messages respectively corresponding to the plurality of communication paths.

S704, the target network node determines the fair bandwidth of each communication path according to the path information corresponding to the network node of each communication path.

S705, the target network node obtains the queue depth of the communication path, and the queue depth is used for representing the time delay of the communication path.

S706, the target network node corrects the fair bandwidth of the communication path according to the queue depth of the communication path.

And S707, the target network node determines the traffic regulation information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path.

And S708, the target network node generates a second message according to the flow regulation information of each communication path.

S709, the target network node sends a second message to the source network node.

S710, the source network node receives the second packet from the target network node.

And S711, the source network node adjusts the flow of at least one communication path in the plurality of communication paths according to the second message.

In this embodiment, the implementation manners of S701 to S711 are the same as the implementation manners of the corresponding steps in the embodiments shown in fig. 3 to fig. 10 of the present application, and the specific implementation manners and technical effects of the steps can be referred to the descriptions in the above embodiments, and are not described herein again.

Fig. 15 is a signaling diagram of a traffic regulation method according to an embodiment of the present application, and as shown in fig. 15, the traffic regulation method according to the embodiment includes:

s801, the source network node sends a first message to the target network node through a plurality of communication paths respectively, wherein the first message is used for acquiring path information corresponding to the network node on the communication path, and the path information is used for determining flow regulation information.

S802, a target network node receives first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network nodes on the communication paths.

And S803, the target network node determines path information corresponding to the network node of each communication path according to the first messages respectively corresponding to the plurality of communication paths.

S804, the target network node encapsulates the path information in the first message corresponding to each of the plurality of communication paths into a second message.

S805, the target network node sends a second message to the source network node.

S806, the source network node receives the second message from the target network node.

S807, the source network node determines fair bandwidth of each communication path according to the path information corresponding to the network node of each communication path.

S808, the source network node acquires the queue depth of the communication path, and the queue depth is used for representing the time delay of the communication path.

And S809, the source network node corrects the fair bandwidth of the communication path according to the queue depth of the communication path.

And S810, the source network node determines the flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path.

S811, the source network node performs traffic regulation on at least one of the plurality of communication paths according to the traffic regulation information of each communication path.

In this embodiment, the implementation manners of S801 to S811 are the same as the implementation manners of the corresponding steps in the embodiments shown in fig. 3 to fig. 10 of the present application, and the specific implementation manners and technical effects of the steps can be referred to the descriptions in the above embodiments, and are not described herein again.

The flow rate adjustment method of the embodiment of the present application is described above in detail, and the flow rate adjustment device of the embodiment of the present application will be described below.

In one example, fig. 16 is a schematic block diagram of a flow rate adjustment device provided in an embodiment of the present application. The traffic adjusting device 9 provided in the embodiment of the present application may be the source network node in the above method embodiment, or may be one or more chips in the source network node. The traffic shaper 9 may be adapted to perform part or all of the functionality of the source network node in the above-described method embodiments. The flow regulating device 9 may comprise the following modules:

the receiving and sending module 91 is configured to send a first message to a target network node through a plurality of communication paths, where the first message is used to obtain path information corresponding to the network node on the communication path, and the path information is used to determine flow adjustment information; receiving a second message from the target network node; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information. Wherein, the transceiver module 91 may perform steps S101-S102 of the method shown in fig. 3, or may perform steps S201-S202 of the method shown in fig. 5, or may perform steps S301-S302 of the method shown in fig. 10.

And the processing module 92 is configured to perform traffic adjustment on at least one communication path of the plurality of communication paths according to the second packet. Wherein, the processing module 92 may execute step S103 of the method shown in fig. 3, or may execute step S303 of the method shown in fig. 10.

The flow rate adjusting device in the embodiment shown in fig. 16 can be used to implement the technical solution in the embodiment shown in fig. 3 in the above method, and the implementation principle and the technical effect are similar, and are not described herein again.

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on multiple communication paths, the processing module 92 is specifically configured to: determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and performing traffic regulation on at least one communication path in the plurality of communication paths according to the traffic regulation information of each communication path. At this point, the processing module 92 may perform steps S203, S204, S205 of the method shown in fig. 5.

In a possible implementation manner, when determining the fair bandwidth of the communication path according to the path information corresponding to the network node of the communication path, the processing module 92 is specifically configured to: determining a key link of the communication path according to path information corresponding to the network node of the communication path; the critical link of the communication path determines the load of the communication path; determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path to the link traffic of the key link; and determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the key link. At this point, processing module 92 may perform steps S2031-S2033 of the method shown in FIG. 7.

In a possible implementation manner, after determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the critical link, the processing module 92 is specifically configured to: acquiring the queue depth of the communication path, wherein the queue depth is used for representing the time delay of the communication path; and correcting the fair bandwidth of the communication path according to the queue depth of the communication path. At this point, the processing module 92 may perform steps S203A-S203B of the method shown in FIG. 7.

Optionally, when the processing module 92 corrects the fair bandwidth of the communication path according to the queue depth of the communication path, it is specifically configured to: determining a correction bandwidth according to a queue depth of a communication path, wherein the queue depth is in direct proportion to the correction bandwidth; and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth. At this point, the processing module 92 may perform step S203B of the method shown in fig. 7.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic, and when determining the traffic adjustment information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path, the processing module 92 is specifically configured to: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; and determining the target utilization rate according to the ratio of the sum of the input flow of each communication path to the sum of the fair bandwidth of each communication path. And determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate. At this point, the processing module 92 may perform steps S2041-S2043 of the method shown in FIG. 7.

In a possible implementation manner, the second packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the processing module 92 is further configured to: determining a flow correction value according to the queue depth; and adjusting the flow of the plurality of communication paths according to the flow correction value.

The flow rate adjusting device in the embodiment shown in fig. 16 may be used to implement the technical solution in any one of the embodiments shown in fig. 3, fig. 5, or fig. 10 in the above method, and the implementation principle and the technical effect are similar, and are not described herein again.

In another example, fig. 17 is a schematic block diagram of a flow rate adjustment device provided in an embodiment of the present application. The traffic conditioning device 10 provided in the embodiment of the present application may be the target network node in the above method embodiment, and may also be one or more chips in the target network node. The traffic conditioning device 10 may be adapted to perform part or all of the functionality of the target network node in the above-described method embodiments. The flow regulating device 10 may comprise the following modules:

the receiving and sending module 101 is configured to receive first messages respectively sent by a source network node through a plurality of communication paths, where the first messages include path information corresponding to the network node on the communication path, and the path information is used to determine flow adjustment information. The transceiver module 101 may perform step S401 of the method shown in fig. 11, or may perform step S601 of the method shown in fig. 13.

The processing module 102 is configured to generate a second message according to the first messages respectively corresponding to the multiple communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information. Wherein the processing module 102 may execute step S402 of the method shown in fig. 11.

The transceiver module 101 is further configured to send a second packet to the source network node. The transceiver module 101 may perform step S403 of the method shown in fig. 11, or may perform step S606 of the method shown in fig. 13.

In a possible implementation manner, when the second packet is used to indicate flow adjustment information, the processing module 102 is specifically configured to: determining path information corresponding to network nodes of each communication path according to first messages respectively corresponding to the plurality of communication paths; determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path; determining flow regulation information of each communication path according to the input flow of each communication path and the fair bandwidth of each communication path; and generating a second message according to the flow regulation information of each communication path. At this time, the processing module 102 may perform steps S602, S603, S604, S605 of the method shown in fig. 13.

In a possible implementation manner, when determining the fair bandwidth of the communication path according to the path information corresponding to the network node of the communication path, the processing module 102 is specifically configured to: determining a key link of the communication path according to path information corresponding to the network node of the communication path; the critical link of the communication path determines the load of the communication path; determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path to the link traffic of the key link; and determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the key link. At this time, the processing module 102 may perform step S603 of the method shown in fig. 13.

In a possible implementation manner, after determining the fair bandwidth of the communication path according to a product of the traffic proportion of the communication path and the link bandwidth of the critical link, the processing module 102 is specifically configured to: acquiring the queue depth of the communication path, wherein the queue depth is used for representing the time delay of the communication path, and the larger the queue depth is, the larger the time delay is; and correcting the fair bandwidth of the communication path according to the queue depth of the communication path. At this point, the process module 102 may perform steps S603A-S603B of the method shown in FIG. 13.

Optionally, when the processing module 102 modifies the fair bandwidth of the communication path according to the queue depth of the communication path, it is specifically configured to: determining a correction bandwidth according to a queue depth of a communication path, wherein the queue depth is in direct proportion to the correction bandwidth; and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth. At this time, the processing module 102 may perform step S603B of the method shown in fig. 13.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic, and when determining the traffic adjustment information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path, the processing module 102 is specifically configured to: acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path; determining a target utilization rate according to the ratio of the sum of the input flows of all the communication paths to the sum of the fair bandwidths of all the communication paths; and determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate. At this point, the processing module 102 may perform step S604 of the method shown in fig. 13.

In a possible implementation manner, the traffic adjustment information includes a target allocation traffic or a target adjustment traffic, and when the processing module 102 generates the second packet according to the traffic adjustment information of each communication path, the processing module is specifically configured to: determining the target regulation flow of each communication path according to the difference value between the target distribution flow of each communication path and the input flow of each communication path, and packaging the target regulation flow into a second message, or; and encapsulating the target distribution flow of each communication path into a second message. At this point, the processing module 102 may perform step S605 of the method shown in fig. 13.

In a possible implementation manner, when the second packet includes path information corresponding to network nodes on multiple communication paths, the processing module 102 is specifically configured to: and encapsulating the path information in the first message corresponding to the plurality of communication paths into a second message. At this point, the processing module 102 may perform step S605 of the method shown in fig. 13.

In a possible implementation manner, the first packet includes a queue depth, where the queue depth is used to characterize a delay size of the communication path, and the processing module 102 is further configured to: determining a flow correction value according to the queue depth; and the flow correction value is arranged in the second message.

The flow rate adjustment device in the embodiment shown in fig. 17 may be used to implement the technical solution in any one of the embodiments shown in fig. 11 or fig. 13 in the above method, and the implementation principle and the technical effect are similar, and are not described herein again.

Fig. 18 is a schematic block diagram of a network device according to an embodiment of the present application. As shown in fig. 18, the network device 11 includes a transmitter 111, a receiver 112, and a processor 113.

Wherein the processor 113 is configured to execute the steps of the embodiment shown in fig. 3, or the processor 113 is configured to execute the steps of the embodiment shown in fig. 5, or the processor 113 is configured to execute the steps of the embodiment shown in fig. 10. The processor 113 is used to implement the modules of fig. 16.

The network device 11 in the embodiment shown in fig. 18 may be configured to execute the technical solution executed by the source network node in the embodiments shown in fig. 12, fig. 14, or fig. 15 in the above method embodiment, or the program of each module in the embodiment shown in fig. 16, which is called by the processor 113 to execute the operation of the above method embodiment, so as to implement each module shown in fig. 16.

The processor 113 may be a controller, and is represented as "controller/processor 113" in fig. 18. The transmitter 111 and the receiver 112 are used to support information transmission and reception between the network device and each device in the network environment in the above-described embodiments, and to support communication between the network device and each device in the network environment in the above-described embodiments.

Further, the network device may also include a memory 114, the memory 114 for storing program codes and data of the network device. Further, the network device may also include a communication interface 115.

Processor 113, such as a Central Processing Unit (CPU), may also be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. The memory 114 may be a single memory or a combination of a plurality of memory elements.

It should be noted that, in the embodiment of the present application, the transmitter 111 included in the network device 11 provided in fig. 18 may perform a transmitting action, the processor 113 performs a processing action, and the receiver may perform a receiving action, corresponding to the foregoing method embodiments. Reference may be made in particular to the method embodiments described above.

Fig. 19 is a schematic block diagram of a network device according to an embodiment of the present application. As shown in fig. 19, the network device 12 includes a transmitter 121, a receiver 122, and a processor 123.

Wherein, the processor 123 is configured to execute the steps of the embodiment shown in fig. 11, or the processor 123 is configured to execute the steps of the embodiment shown in fig. 13. Processor 123 is used to implement the modules of fig. 17.

The network device 12 in the embodiment shown in fig. 19 may be configured to execute the technical solution executed by the target network node in the embodiments shown in fig. 12, fig. 14, or fig. 15 in the above method embodiment, or the program of each module in the embodiment shown in fig. 17, which is called by the processor 123 to execute the operation of the above method embodiment, so as to implement each module shown in fig. 17.

The processor 123 may be a controller, and is shown as "controller/processor 123" in fig. 19. The transmitter 121 and the receiver 122 are used to support information transmission and reception between the network device and each device in the network environment in the above-described embodiments, and to support communication between the network device and each device in the network environment in the above-described embodiments.

Further, the network device 12 may also include a memory 124, the memory 124 for storing program codes and data for the network device. Further, the network device may also include a communication interface 125.

Processor 123, such as a Central Processing Unit (CPU), may also be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. The memory 124 may be a single memory or a combination of a plurality of memory elements.

It should be noted that, in the network device 12 of fig. 19 provided in this embodiment of the present application, the transmitter 121 may perform a transmitting action, the processor 123 performs a processing action, and the receiver may perform a receiving action, corresponding to the foregoing method embodiment. Reference may be made in particular to the method embodiments described above.

Exemplarily, fig. 20 is a schematic block diagram of a structure of another network device provided in the embodiment of the present application, and as shown in fig. 20, the network device 13 provided in the embodiment includes: a transceiver 131, a memory 132, a processor 133 and computer programs.

Wherein the processor 133 is configured to control the transceiver 131 to transmit and receive signals, and the computer program is stored in the memory 132 and configured to be executed by the processor 133 to implement the method provided by any implementation manner corresponding to fig. 3-10 of the present application.

The transceiver 131, the memory 132, and the processor 133 are connected by a bus 134.

The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 3 to fig. 10 can be understood, and are not described in detail herein.

Exemplarily, fig. 21 is a schematic block diagram of a structure of another network device provided in the embodiment of the present application, and as shown in fig. 21, the network device 14 provided in the embodiment includes: a transceiver 141, a memory 142, a processor 143, and computer programs.

The processor 143 is configured to control the transceiver 141 to transmit and receive signals, and the computer program is stored in the memory 142 and configured to be executed by the processor 143 to implement the method provided by any one of the implementations corresponding to fig. 11 and 13.

The transceiver 141, the memory 142, and the processor 143 are connected by a bus 144.

The related description may be understood by referring to the related description and effects corresponding to the steps in the embodiment corresponding to fig. 11 and fig. 13, and redundant description is not repeated here.

Embodiments of the present application further provide a computer-readable storage medium, which includes computer code, when executed on a computer, causes the computer to execute the method provided in any one of the implementation manners corresponding to fig. 3-15.

The embodiment of the present application further provides a computer program product, which includes a program code, and when the computer program product is executed by a computer, the program code executes the method provided in any implementation manner corresponding to fig. 3 to 15.

The embodiment of the application also provides a chip which comprises a processor. The processor is configured to call and execute a computer program stored in the memory to perform corresponding operations and/or procedures performed by the source network node or the target network node in the traffic regulating method according to any of the implementations corresponding to fig. 3 to 15. Optionally, the chip further comprises a memory, the memory is connected with the processor through a circuit or a wire, and the processor is used for reading and executing the computer program in the memory. Further optionally, the chip further comprises a communication interface, and the processor is connected to the communication interface. The communication interface is used for receiving data and/or information needing to be processed, and the processor acquires the data and/or information from the communication interface and processes the data and/or information. The communication interface may be an input output interface. In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, 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. The procedures or functions according to the embodiments of the present application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in the embodiments of the present application may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

Claims

1. A traffic conditioning method, applied to a source network node, the method comprising:

respectively sending a first message to a target network node through a plurality of communication paths, wherein the first message is used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information;

receiving a second message from the target network node; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information;

and adjusting the flow of at least one communication path in the plurality of communication paths according to the second message.

2. The method of claim 1, wherein the communication path comprises at least one link, and wherein the path information indicates a load of the link where the network node is located.

3. The method according to claim 1 or 2, wherein the first packet includes request information for requesting the network node to record corresponding path information in the first packet.

4. A method according to any of claims 1-3, wherein the path information comprises at least one of:

identification of the communication path, message sending timestamp, link bandwidth, link traffic, link utilization, input traffic of the communication path, and queue depth of the communication path.

5. The method according to any one of claims 1 to 4, wherein when the second packet includes path information corresponding to network nodes on the plurality of communication paths, performing traffic adjustment on at least one communication path of the plurality of communication paths according to the second packet includes:

determining fair bandwidth of each communication path according to path information corresponding to the network node of each communication path;

determining traffic regulation information of each communication path according to the input traffic of each communication path and the fair bandwidth of each communication path;

and performing traffic regulation on at least one communication path in the plurality of communication paths according to the traffic regulation information of each communication path.

6. The method of claim 5, wherein determining the fair bandwidth of the communication path according to the path information corresponding to the network node of the communication path comprises:

determining a key link of the communication path according to path information corresponding to the network node of the communication path; the critical link of the communication path determines the load of the communication path;

determining the traffic ratio of the communication path according to the ratio of the input traffic of the communication path to the link traffic of the key link;

and determining the fair bandwidth of the communication path according to the product of the traffic ratio of the communication path and the link bandwidth of the key link.

7. The method of claim 6, wherein after determining the fair bandwidth of the communication path according to a product of the traffic fraction of the communication path and the link bandwidth of the critical link, further comprising:

acquiring the queue depth of the communication path, wherein the queue depth is used for representing the time delay of the communication path;

and correcting the fair bandwidth of the communication path according to the queue depth of the communication path.

8. The method of claim 7, wherein modifying the fair bandwidth of the communication path based on the queue depth of the communication path comprises:

determining a modified bandwidth according to a queue depth of the communication path, wherein the queue depth is proportional to the modified bandwidth;

and subtracting the corrected bandwidth from the fair bandwidth of the communication path to obtain the corrected fair bandwidth.

9. The method according to any of claims 5-8, wherein the traffic adjustment information comprises target allocated traffic, and determining the traffic adjustment information for each of the communication paths according to the incoming traffic for each of the communication paths and the fair bandwidth for each of the communication paths comprises:

acquiring the sum of input flow of each communication path and the sum of fair bandwidth of each communication path;

determining a target utilization rate according to the ratio of the sum of the input flows of the communication paths to the sum of the fair bandwidths of the communication paths;

and determining the target distribution flow of each communication path according to the product of the fair bandwidth of each communication path and the target utilization rate.

10. The method according to any of claims 1-9, wherein the second packet includes a queue depth, and the queue depth is used to characterize a delay size of the communication path, and the method further comprises:

determining a flow correction value according to the queue depth;

and carrying out flow regulation on the plurality of communication paths according to the flow correction value.

11. A traffic conditioning method, applied to a target network node, the method comprising:

receiving first messages respectively sent by a source network node through a plurality of communication paths, wherein the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information;

generating second messages according to the first messages respectively corresponding to the plurality of communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information;

and sending the second message to the source network node.

12. The method of claim 11, wherein the communication path comprises at least one link, and wherein the path information indicates a load of the link where the network node is located.

13. The method according to claim 11 or 12, wherein the path information comprises at least one of:

14. The method according to any one of claims 11 to 13, wherein generating the second packet according to the first packets respectively corresponding to the plurality of communication paths when the second packet is used to indicate traffic adjustment information includes:

determining path information corresponding to network nodes of the communication paths according to first messages respectively corresponding to the communication paths;

and generating the second message according to the flow regulation information of each communication path.

15. The method of claim 14, wherein determining the fair bandwidth of the communication path according to the path information corresponding to the network node of the communication path comprises:

16. The method of claim 15, wherein after determining the fair bandwidth of the communication path according to a product of the traffic fraction of the communication path and the link bandwidth of the critical link, further comprising:

17. The method of claim 16, wherein modifying the fair bandwidth of the communication path based on the queue depth of the communication path comprises:

18. The method according to any of claims 14-17, wherein the traffic adjustment information comprises target allocated traffic, and wherein determining the traffic adjustment information for each of the communication paths based on the incoming traffic for each of the communication paths and the fair bandwidth for each of the communication paths comprises:

19. The method according to any of claims 14-18, wherein the traffic conditioning information comprises a target allocated traffic or a target conditioned traffic, and wherein generating the second packet according to the traffic conditioning information of each of the communication paths comprises:

determining a target regulation flow of each communication path according to a difference value between a target distribution flow of each communication path and an input flow of each communication path, and encapsulating the target regulation flow into the second message, or;

and encapsulating the target distribution flow of each communication path into the second message.

20. The method according to any one of claims 11 to 13, wherein generating a second packet according to the first packets respectively corresponding to the plurality of communication paths when the second packet includes path information corresponding to the network nodes on the plurality of communication paths comprises:

and encapsulating the path information in the first message corresponding to the plurality of communication paths into the second message.

21. The method according to any of claims 11-20, wherein the first packet includes a queue depth, and wherein the queue depth is used to characterize a delay size of the communication path, and wherein the method further comprises:

determining a flow correction value according to the queue depth; wherein the flow correction value is set in the second message.

22. A traffic conditioning device, for application to a source network node, the device comprising a transceiver module and a processing module, wherein:

the system comprises a receiving and sending module, a sending and receiving module and a sending and receiving module, wherein the receiving and sending module is used for respectively sending a first message to a target network node through a plurality of communication paths, the first message is used for acquiring path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information;

the receiving and sending module is also used for receiving a second message from the target network node; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information;

23. A traffic conditioning device, for application to a target network node, the device comprising a transceiver module and a processing module, wherein:

the system comprises a receiving and sending module, a sending and receiving module and a sending and receiving module, wherein the receiving and sending module is used for receiving first messages respectively sent by a source network node through a plurality of communication paths, the first messages comprise path information corresponding to the network node on the communication paths, and the path information is used for determining flow regulation information;

the processing module is used for generating second messages according to the first messages respectively corresponding to the plurality of communication paths; the second message includes path information corresponding to network nodes on the plurality of communication paths, or the second message is used for indicating flow regulation information;

and the transceiver module is further configured to send the second packet to the source network node.

24. A network device, characterized in that the network device comprises: a processor, a memory, and a transceiver;

the processor is used for controlling the transceiver to transmit and receive signals;

the memory is used for storing a computer program;

the processor is further configured to invoke and execute the computer program stored in the memory, so that the network device performs the method of any of claims 1 to 11.

25. A network device, characterized in that the network device comprises: a processor, a memory, and a transceiver;

the memory is used for storing a computer program;

the processor is further configured to invoke and execute the computer program stored in the memory, so that the network device performs the method of any of claims 12 to 21.

26. A computer readable storage medium comprising computer code which, when run on a computer, causes the computer to perform the method of any of claims 1 to 21.