WO2023280004A1

WO2023280004A1 - Network configuration method, device and system

Info

Publication number: WO2023280004A1
Application number: PCT/CN2022/101726
Authority: WO
Inventors: 张嘉怡; 王童童; 高涛; 布亚德安妮; 阿金萨米
Original assignee: 华为技术有限公司
Priority date: 2021-07-05
Filing date: 2022-06-28
Publication date: 2023-01-12
Also published as: CN115589602A

Abstract

Embodiments of the present application disclose a network configuration method, a device and a system. According to traffic acquisition information of a data flow and SLA information corresponding to the data flow, a first device may acquire shaper parameters corresponding to the data flow and the SLA information of the data flow, and can relatively accurately shape the data flow by means of a shaper, so that the processed data flow meets transmission requirements indicated by the SLA information. On the basis of the traffic acquisition information of the data flow, the shaper parameters can be more accurately and flexibly matched with service requirements corresponding to the data flow, thereby achieving differentiated assurances for service requirements of data flows of different service types.

Description

A network configuration method, device and system

This application claims the priority of the Chinese patent application with the application number 202110759176.5 and the title of the invention "a network configuration method, device and system" submitted to the State Intellectual Property Office of China on July 05, 2021, the entire contents of which are incorporated by reference in this application.

technical field

The present application relates to the technical field of communications, and in particular to a network configuration method, device and system.

Background technique

A shaper (shaper) is used to adjust the transmission rate and other aspects of the data stream transmitted in the network. The data flow burst can be limited by the shaper, so as to realize relatively stable data flow transmission, prevent problems such as network congestion or transmission jitter, and meet the business requirements of data flow transmission.

At present, the ultra-reliable low-latency communication (URLLC) multi-service of the fifth-generation (5G) technology has strict requirements on the quality of service (QoS) . Moreover, services of different service types have different service requirements that need to be met. It is necessary for the network to reasonably allocate network resources based on business requirements to meet the corresponding business requirements of different business types.

However, the shaper parameters used to adjust the data flow in the shaper are relatively fixed, so that the data flow adjusted based on the shaper parameters cannot meet the service requirements in some business scenarios. How to determine the shaper parameters of the shaper to meet the business requirements of data stream transmission is a technical problem that needs to be solved.

Contents of the invention

The embodiment of the present application provides a network configuration method, device and system, which can determine the shaper parameters according to the traffic collection information of the data flow and the service level agreement (service level agreement, SLA) information corresponding to the data flow, so that the shaper parameters can be used The adjusted data flow can meet the transmission requirements indicated by the SLA information corresponding to the data flow, and match the service requirements corresponding to the data flow.

The technical solutions provided by the embodiments of the present application are as follows.

In a first aspect, a network configuration method is provided, the method comprising: a first device acquires traffic collection information corresponding to a data flow, and determines the shaping of the shaper based on the obtained traffic collection information and the SLA information corresponding to the data flow device parameters. Wherein, the shaper parameter is used to configure the shaper, so that the shaper adjusts the data flow to meet the transmission requirements indicated by the SLA information. The shaper parameters determined according to the traffic collection information of the data stream and the corresponding SLA information of the data stream are more compatible with the data stream and the SLA information of the data stream, and can realize the shaping process of the data stream through the shaper more accurately, so that the processing The subsequent data flow meets the transmission requirements indicated by the SLA information.

In a possible implementation manner, the first device first determines the target bandwidth, and then determines the shaper parameters according to the target bandwidth. The first device determines a target bandwidth based on the acquired traffic collection information of the data flow and SLA information corresponding to the data flow, and determines a shaper parameter according to the target bandwidth. Wherein, the target bandwidth is the minimum value of the available bandwidth for transmitting the data flow on the premise of meeting the transmission requirements indicated by the SLA information. Based on the target bandwidth, more accurate shaper parameters can be determined, so that the adjusted data flow can meet the transmission requirements indicated by the SLA information corresponding to the data flow.

In a possible implementation manner, the first device may first determine the range of the target bandwidth, and then select the target bandwidth from within the range of the target bandwidth. The first device first determines the range of the target bandwidth according to the traffic collection information, and then determines the target bandwidth within the range of the target bandwidth according to the SLA information corresponding to the data flow. The range of the target bandwidth determined based on the flow collection information may be matched with the data flow. The target bandwidth matching the SLA information corresponding to the data flow is determined within the range of the target bandwidth. Therefore, the target bandwidth matching the data flow and the SLA information corresponding to the data flow can be obtained, so as to meet the transmission requirement indicated by the SLA information.

In a possible implementation manner, the first device may determine the range of the target bandwidth in the following two manners.

In the first manner, the first device determines the range of the target bandwidth according to the reference value of the target bandwidth and the correction value of the target bandwidth. Wherein, the reference value of the target bandwidth is determined according to the traffic collection information, and the correction value of the target bandwidth indicates the amount of fluctuation of the target bandwidth relative to the reference value.

In the second manner, the first device determines the range of the target bandwidth based on a distribution fitting algorithm and traffic collection information.

In a possible implementation manner, the flow collection information includes the length of packets of the data flow in multiple collection periods. Correspondingly, the first device may determine the burst volume of the data stream according to the acquired traffic collection information of the data stream, and then calculate the target bandwidth by using the burst volume and SLA information corresponding to the data stream. Wherein, the burst amount is the length of the message corresponding to each acquisition period among the plurality of acquisition periods.

In a possible implementation, when the degree of congestion is greater than the threshold, the first device adopts one or more of the following three ways to adjust to meet the transmission requirements indicated by the SLA information and the degree of congestion is less than or equal to the threshold . Wherein, the degree of congestion is determined according to the remaining capacity of the forwarding device. The remaining capacity refers to the remaining forwarding capability of the forwarding device when the committed forwarding delay of the forwarding device is guaranteed. The committed forwarding delay is the preset delay for data streams waiting to be processed in the forwarding device.

In the first manner, the first device adjusts the SLA information, so that the shaper parameters determined according to the traffic collection information and the adjusted SLA information adjust the data flow.

In the second manner, the first device adjusts the queue into which the data flow enters.

In the third way, the first device adjusts the transmission path of the data flow, so that the data flow is transmitted through the transmission path of the data flow.

In a possible implementation, when the delay in transmitting data streams from the source to the destination, or the estimated value of the delay in transmitting data streams from the source to the destination, does not meet the transmission requirements of the SLA information , the first device adopts one or more of the following three ways to adjust to meet the transmission requirement indicated by the SLA information.

Optionally, the SLA information includes the upper bound of the target delay, and the upper bound of the target delay indicates the upper bound of the delay of the data flow from the source end to the destination end.

Optionally, the target delay includes shaping delay, and the shaping delay indicates the delay during processing of the data flow in the shaper.

Optionally, the target delay further includes one or more of a fixed delay and a network forwarding delay, and the fixed delay includes one or more of a propagation delay, a device processing delay, and a port delay. Among them, the propagation delay is the delay of the data stream propagating in the transmission medium, the device processing delay is the delay of the device processing the data stream, and the port transmission delay is the delay of transmitting the data stream through the port. The network forwarding delay is the preset delay for the data flow waiting to be processed in the forwarding device during the process from the source end to the destination end.

Optionally, the network forwarding delay indicates the sum of committed forwarding delays of multiple forwarding devices transmitting data streams, where the committed forwarding delay is a preset delay for data streams waiting to be processed in the forwarding devices.

Optionally, the network forwarding delay is determined according to preset forwarding bandwidths of multiple forwarding devices transmitting data streams, and the preset forwarding bandwidth is the preset bandwidth of data streams forwarded by the forwarding devices.

Optionally, the target delay further includes one or more of a fixed delay and an actual forwarding delay, and the actual forwarding delay indicates a delay for a data flow from the source end to the destination end to be processed in the forwarding device.

Optionally, the SLA information includes a cache upper bound, and the cache upper bound is a minimum value of an available cache of a device including a shaper among devices transmitting data streams.

Optionally, the SLA information further includes a reliability probability, where the reliability probability is a probability of meeting a transmission requirement indicated by the SLA information corresponding to the data flow.

In a possible implementation manner, the first device may acquire the traffic collection information of the data flow through the second device. Wherein, the second device generates traffic collection information of the data flow, and sends it to the first device. The second device is a device for transmitting data streams.

In another possible implementation manner, the first device may acquire traffic collection information of the data flow collected and generated by the first device.

Optionally, the flow collection information includes statistical values of packet lengths of the data flow in multiple collection periods. The statistical value includes an average value, and the average value indicates the length of the plurality of packets in the collected data stream and the ratio of the number of collection cycles for collecting the plurality of packets.

Optionally, the statistical value further includes one or more of second-order moments and fourth-order moments. The second-order moment indicates the ratio of the sum of the squares of the lengths of multiple packets in the collected data stream to the number of collection cycles experienced in collecting the multiple packets. The fourth moment indicates the ratio of the sum of the fourth powers of the lengths of multiple packets in the collected data stream to the number of collection cycles experienced in collecting the multiple packets.

In a possible implementation manner, after the first device determines the shaper parameter of the shaper, the first device may send the shaper parameter to the third device. The third device is a device for transporting data streams including a shaper.

Optionally, the first device is a control device or a device for transmitting data streams.

Optionally, the control device is a central network control CNC device.

Optionally, the shaper parameters include at least one of token bucket depth and token generation rate.

Optionally, the shaper parameters include at least one of a credit accumulation rate and a credit consumption rate.

In a second aspect, a first device is provided, and the first device has a function of implementing the behavior of the first device in the above method. The functions may be implemented based on hardware, or corresponding software may be implemented based on hardware. Hardware or software includes one or more modules corresponding to the above-mentioned functions. In an implementation manner, the first device includes: an acquisition unit and a processing unit. Wherein, the acquiring unit is configured to acquire traffic collection information of the data stream. The processing unit is configured to determine the shaper parameters according to the traffic collection information and the SLA information corresponding to the data flow, and the shaper parameters are used by the shaper to adjust the data flow to meet the transmission requirements indicated by the SLA information.

In a possible design, the structure of the first device includes a processor and an interface, and the processor is configured to support the first device to perform corresponding functions in the foregoing method. The interface is used to support the communication between the first device and the second device, and receives the information or instructions involved in the above method from the second device, and the interface is also used to support the communication between the first device and the third device, and sends the information to the second device. The third device sends the information or instructions involved in the above methods. The first device may further include a memory for coupling with the processor, which stores necessary program instructions and data of the first device.

In another possible design, the first device includes: a processor, a transmitter, a receiver, a random access memory, a read only memory, and a bus. Wherein, the processor is respectively coupled to the transmitter, the receiver, the random access memory and the read-only memory through the bus. Wherein, when the first device needs to be operated, the basic input/output system solidified in the read-only memory or the bootloader boot system in the embedded system is started to guide the first device into a normal operation state. After the first device enters the normal running state, run the application program and the operating system in the random access memory, so that the processor executes the method in the first aspect or any possible implementation manner of the first aspect.

In a third aspect, a first device is provided, and the first device includes: a main control board and an interface board, and may further include a switching fabric board. The first device is configured to execute the method in the first aspect or any possible implementation manner of the first aspect. Specifically, the first device includes a module for executing the method in the first aspect or any possible implementation manner of the first aspect.

In a fourth aspect, a first device is provided, and the first device includes a controller and a first forwarding sub-device. The first forwarding sub-device includes: an interface board, and may further include a switching fabric board. The first forwarding sub-device is configured to perform the function of the interface board in the third aspect, and further, may also perform the function of the switching fabric board in the third aspect. The controller includes receiver, processor, transmitter, random access memory, read only memory and bus. Wherein, the processor is respectively coupled to the receiver, the transmitter, the random access memory and the read-only memory through the bus. Wherein, when the controller needs to be operated, the basic input/output system solidified in the read-only memory or the bootloader boot system in the embedded system is started to guide the controller into a normal operation state. After the controller enters the normal operation state, the application program and the operating system are run in the random access memory, so that the processor executes the functions of the main control board in the third aspect.

In the fifth aspect, a computer storage medium is provided, which is used to store the programs, codes or instructions used by the above-mentioned first device. When the processor or hardware device executes these programs, codes or instructions, the first aspect in the above-mentioned first aspect can be completed. A function or step of a device.

According to a sixth aspect, a network system is provided, and the network system includes a first device and a second device. Wherein, the second device is a device for transmitting data streams. The second device is configured to collect traffic collection information of the data stream, and send the traffic collection information of the data stream to the first device. The first device is configured to receive traffic collection information of the data stream sent by the second device, and is further configured to determine shaper parameters according to the traffic collection information and SLA information corresponding to the data stream. The shaper parameters are used by the shaper to adjust the data flow to meet the transmission requirements indicated by the SLA information.

Optionally, the network system further includes a third device. Wherein, the first device is further configured to send the shaper parameter to the third device. The third device is configured to receive the shaper parameters sent by the first device, and configure the shaper according to the shaper parameters. The third device is a device for transporting data streams including a shaper.

Through the above solution, the first device can obtain the shaper parameters corresponding to the data flow and the SLA information of the data flow according to the traffic collection information of the data flow and the SLA information corresponding to the data flow, and can achieve relatively accurate data shaping through the shaper. The flow is shaped so that the processed data flow meets the transmission requirements indicated by the SLA information. Based on the flow collection information of the data flow, the parameters of the shaper can be more accurately and flexibly matched with the service requirements corresponding to the data flow, and the differentiated guarantee for the service requirements of the data flow of different service types can be realized.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments described in this application. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of a network architecture provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of another network architecture provided by an embodiment of the present application;

FIG. 3 is an interactive schematic diagram of a network configuration method provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a message format carrying SLA information of a data flow provided by an embodiment of the present application;

FIG. 5 is a schematic flowchart of a network configuration method provided in an embodiment of the present application;

FIG. 6 is a schematic structural diagram of a first device according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a hardware structure of a first device according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a hardware structure of another first device according to an embodiment of the present application.

detailed description

The traditional technology and the network configuration method, device and system provided by the embodiments of the present application are introduced below with reference to the accompanying drawings.

When using a network to transmit a data stream, it is necessary to meet the service requirements of the service type to which the data stream belongs. Moreover, in some possible cases, the transmitted data flow may be a dynamic data flow, which has a certain degree of burstiness, randomness and dynamics. The dynamic data flow may be, for example, a data flow with relatively large traffic fluctuations within a certain period of time, or a data flow with relatively large transmission rate fluctuations, or a data flow that causes micro-bursts to occur on the network. If the data stream is directly transmitted, it is easy to cause problems such as network congestion or transmission jitter, and it is difficult to meet the service requirements corresponding to the data stream. Therefore, it is necessary to shape the data stream so that the processed data stream has a relatively definite maximum burst and a relatively stable transmission rate, reduce possible network problems during data stream transmission, and meet the corresponding business requirements of the data stream .

In a possible implementation manner, a shaper may be used to perform shaping processing on the data stream. The shaper is used to adjust the traffic and burst of the data flow, so that the data flow shaped by the shaper is transmitted at a relatively uniform speed. Shapers include shaper parameters that indicate shaping adjustments. In the traditional technology, the parameters of the shaper are mainly determined based on the data flow transmission requirements of the source, and a certain amount of manual intervention and adjustment is performed based on experience, so the parameters of the shaper are relatively fixed. The data flow shaped by the shaper cannot meet the service requirements well, and it is difficult to adapt to the actual needs of the network.

Based on this, embodiments of the present application provide a network configuration method, device, and system, which determine shaper parameters by acquiring traffic collection information of a data flow and SLA information corresponding to the data flow. The determined shaper parameters adjust the data flow more accurately to ensure that the data flow shaped by the shaper meets the transmission requirements of the corresponding SLA information indication of the data flow, and realize the provision of corresponding SLA information indication based on different data flows Differentiated guarantees for transport requirements.

Among them, SLA is an agreement mutually recognized by both parties on the quality, level, and performance of network services reached between enterprises providing network services and customers. The specific content of the network service performance agreed in the SLA information is determined by the specific business requirements. In a possible implementation manner, the SLA information includes service level parameters. The service level parameter may indicate the service index to be achieved by the specific network service. For example, the service level parameter may be the upper bound of the target delay, and the upper bound of the target delay is used to indicate the upper bound of the transmission delay of the data flow from the source end to the destination end. The service level parameter may also be a cache upper bound, and the cache upper bound is used to indicate the minimum value of the available cache of the device transmitting the data stream. In addition, the SLA information may also include the reliability probability of transmitting the data flow meeting the service level parameter. For example, if the SLA information includes the upper bound of the target delay, the SLA information may further include a reliability probability that the delay is less than or equal to the upper bound of the target delay when the data stream is transmitted. If the SLA information includes the cache upper bound, the SLA information may further include a reliability probability that the available cache of the device transmitting the data stream is greater than or equal to the cache upper bound.

The network configuration method proposed in the embodiment of the present application can be applied to URLLC scenarios in 5G, and these scenarios need to meet service requirements of high reliability and low latency. Such as industrial manufacturing automation scenarios, electric power automation scenarios, and Internet of Vehicles scenarios, etc., these scenarios have strict requirements on the reliability probability of transmission. For example, the solutions in the embodiments of this application can be used to provide highly reliable bounded delay guarantees for smart grid differential protection services, and can also provide highly reliable, bounded delay guarantees for service flows of control services in campus networks. Latency forwarding service. It can also be used in smart factories, based on wired Ethernet or wireless networks, to provide high-reliability bounded delay guarantees for sensors to collect business traffic, industrial control traffic, and video surveillance traffic.

Taking FIG. 1 as an example, the network architecture applicable to the solution of the embodiment of the present application will be introduced below. The network 100 shown in FIG. 1 includes a control device 101 and network devices 102-104. The sending end device 105 is the source end device for sending the data flow, and the receiving end device 106 is the destination end device for the data flow. The network devices 102 - 104 are forwarding devices on the transmission path of the data flow, and are used to send the data flow from the sending end device 105 to the receiving end device 106 in the network 100 . The network device 102 and the network device 104 are edge nodes of the network, and the network device 103 is connected to the network device 102 and the network device 104 respectively. The control device 101 is respectively connected to the network devices 102-104 to implement management and resource deployment of the network devices 102-104. FIG. 1 is only a schematic diagram of an exemplary system architecture of the embodiment of the present application, and should not limit the network architecture of this solution. For example, the network 100 in FIG. forwarding device. For another example, the network 100 in FIG. 1 may further include multiple subnets, and each subnet includes one or more forwarding devices.

In this embodiment of the application, the sending end device 105 and the receiving end device 106 in FIG. 1 may be terminal devices or servers. Terminal equipment, also known as user equipment (UE), mobile station (mobile station, MS), mobile terminal (mobile terminal, MT), terminal, etc., is a device that provides voice and/or data connectivity to users. device, or a chip set in the device, for example, a handheld device with a wireless connection function, a vehicle-mounted device, and the like. At present, examples of some terminal devices are: mobile phones, desktop computers, tablet computers, notebook computers, handheld computers, mobile internet devices (mobile internet device, MID), wearable devices, virtual reality (virtual reality, VR) equipment, augmented reality (augmented reality, AR) equipment, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical surgery, smart grid Wireless terminals in transportation safety, wireless terminals in smart city, wireless terminals in smart home, and home gateway devices supporting 5G access (5G-residential gateway) , 5G-RG) etc.

The network devices 102-104 in FIG. 1 can be in the form of hardware or a combination of software and hardware, and can be an independent device, such as a switch, a router, and other devices with forwarding functions, or it can be a server deploying a virtual router or a virtual switch, or it can be It is a functional module or a combination of multiple functional modules on a network device, which can be selected and designed according to specific scenario requirements. The network devices 102 - 104 are used to forward the data flow in the network 100 .

The control device 101 in FIG. 1 may specifically be a central network control (Central Network Controller, CNC) device.

The control device may be an independent physical device as shown in FIG. 1 , that is, it is physically independent from the network devices 102-104. Referring to FIG. 2 , the control device can also be integrated as a functional unit on any one of the network devices 102 - 104 , or on the sending end device 105 , or on the receiving end device 106 . The control device can also be split into several sub-functional units and deployed on the devices 102-106 in a distributed manner. As long as the control device has logically corresponding calculation, management and control functions, the embodiment of the present application does not limit the existence form of the control device.

In combination with the schematic diagram of the network architecture shown in FIG. 1, FIG. 3 is an interactive schematic diagram of a network configuration method provided in the embodiment of the present application. The network configuration method provided in the embodiment of the present application includes the following steps:

S301: The second device generates traffic collection information of a data stream.

In this embodiment of the present application, the second device is a device for transmitting data streams. As shown in FIG. 1 , the second device may be any of the network devices 102 - 104 , the sending end device 105 , and the receiving end device 106 in FIG. 1 .

The second device collects the transmitted data flow to obtain traffic collection information of the data flow. Wherein, the data flow may be a single service flow, or may be an aggregation flow obtained by converging multiple service flows.

The traffic collection information of the data flow changes in real time along with the data flow. Wherein, the flow collection information may include the length of the packet in at least one collection period of the data flow. The counting unit of the acquisition period may be a time unit such as microsecond (microsecond, μs), millisecond (millisecond, ms), or second (second, s). The counting unit of the message length is bit (binary digit, BIT) or byte (byte).

Based on the two methods of obtaining the length of the message, the following describes how to obtain the length of the message in at least one collection period:

Method 1: Make statistics on the packet length of the data stream in each collection cycle.

For example, the second device collects the accumulated packet length in the data stream at a collection period ΔT _k to obtain the sequence A _k . Wherein, ΔT _k =T _k −T _k-1 , T _k is the sampling time, k=1, . . . , N, N is the number of samples.

The collection period ΔT _k can be a constant value ΔT or a variable value, which can be specifically set according to the collection requirements of the data stream. For example, the acquisition period ΔT may be a constant value of 100ms.

Method 2: Determine the packet length of the data stream in each collection cycle according to the time stamp and packet length of the obtained packet.

The second device obtains the time stamp and the packet length of each packet. According to the time stamp of each message, determine the collection period to which the message belongs. Then, according to the message length of each message, the cumulative message length of the data stream in each collection period is determined.

For example, the second device obtains the time stamp t _j and the packet length B _j of each packet in the data stream. Wherein, j is the number of packets in the obtained data stream. The lengths of the packets corresponding to the time stamps belonging to the collection period ΔT _k are accumulated to obtain the cumulative packet length A _k within the collection period ΔT _k , expressed as {sampling time T _k , cumulative packet length A _k }. Among them, the accumulative message length A _k represents the sum of the message lengths sampled at the sampling time T _k , and can also be understood as the number of messages arriving between the last sampling time T _k-1 and the current sampling time, that is, ΔT _k sum of text lengths.

In a possible implementation, the sampling time and the cumulative message length {T _k , A _k } can be stored in a double-precision format, and the storage space occupied by the sampling data of N points is 8 byte*2*N.

Method 2 can obtain a relatively comprehensive timestamp and packet length of each packet in the data stream, making it more flexible to obtain traffic collection information of the data stream, and also facilitates the analysis based on the timestamp and packet length of each packet The accumulated packet length in the collection cycle is determined.

In a possible implementation, in order to facilitate the transmission of traffic collection information to the first device, the second device may first preprocess the lengths of packets of the collected data streams in multiple collection periods to obtain multiple collection Statistical value of the length of packets in a period. The statistical value includes an average value of the lengths of the packets in multiple collection periods, and the average value indicates the ratio of the lengths of the multiple packets in the collected data stream to the number of collection cycles experienced in collecting the multiple packets. Taking the length of the message in the data stream corresponding to each acquisition period ΔT _k above as _an example, the average value U1 is expressed by formula ( ₁ ):

U ₁ =(A ₁ +…+A _k )/K (1)

In addition, statistical values may also include statistical values such as second-order moments, covariance, and fourth-order moments. Wherein, the second-order moment indicates the ratio of the sum of the squares of the lengths of multiple packets in the collected data stream to the number of collection cycles experienced in collecting the multiple packets. The fourth moment indicates the ratio of the sum of the fourth powers of the lengths of multiple packets in the collected data stream to the number of collection cycles experienced in collecting the multiple packets. The type of the specific statistical value included in the statistical value may be determined according to the manner of determining the parameters of the shaper.

The second-order moment, covariance and fourth-order moment can be represented by formulas (2)-(4):

U ₂ ＝(A ₁ ² +…+A _k ² )/K (2)

U ₃ ＝(A ₁ ×A ₂ +A ₂ ×A ₃ ...+A _k ×A _k-1 )/(K-1) (3)

U ₄ ＝(A ₁ ⁴ +…+A _k ⁴ )/K (4)

In the embodiment of the present application, by preprocessing the obtained packet lengths in multiple collection periods, a statistical value that more accurately reflects the flow change of the data stream can be obtained. In addition, the amount of data included in the flow collection information generated based on the preprocessing result is small, which facilitates the transmission of flow collection information from the second device to the first device and reduces the amount of transmitted data.

S302: The second device sends traffic collection information of the data flow to the first device.

In this embodiment of the present application, the first device may be the control device 101 in FIG. 1 .

In a possible implementation manner, the second device may send the traffic collection information of the data flow to the first device in a type-length-value (tag length value, TLV) format.

The second device may send the traffic collection information of the data flow within the period to the first device at a certain period. The period for the second device to send the traffic collection information may be greater than or equal to the period for collecting the traffic collection information of the data stream. For example, the period for collecting traffic collection information of the data stream may be 100ms, and the period for sending traffic collection information may be 500ms.

S303: The first device determines shaper parameters according to the traffic collection information and the SLA information corresponding to the data flow.

In this embodiment of the present application, the trigger condition for the first device to determine the shaper parameter is not limited. It can be triggered by a set time, for example, timing trigger to determine the parameters of the shaper; it can also be triggered by a set condition, for example, the transmitted data flow meets the condition that needs to be shaped and adjusted.

The SLA information corresponds to the data flow, and is used to indicate the transmission requirements to be met by the transmission of the data flow. The SLA information corresponding to the data flow is relatively fixed. The first device may acquire SLA information corresponding to the data stream at an initial stage of transmitting the data stream. Afterwards, the updated SLA information may be obtained again after the SLA information corresponding to the data stream changes.

In a possible implementation manner, the first device may acquire the SLA information corresponding to the data flow based on the locally stored correspondence between the data flow and the SLA information. In another possible implementation manner, the first device may obtain the SLA information corresponding to the data flow from other devices through a user network interface (user network interface, UNI) or a user centralized configuration (centralized user configuration, CUC). For example, the first device may acquire SLA information corresponding to the data flow through the second device. The second device may be the sending end device 105 shown in FIG. 1 , or may be the network devices 102-103. Wherein, the second device that sends the SLA information may be the same device as the second device that sends the traffic collection information. For example, the second device that sends the SLA information and the second device that sends the traffic collection information may be the network device 102 in FIG. 1 . The second device that sends the SLA information may also be a different device from the second device that sends the traffic collection information. For example, the second device sending the SLA information is the sending end device 105 in FIG. 1 , and the second device sending the traffic collection information is the network device 102 in FIG. 1 .

For the implementation of the above-mentioned first device obtaining SLA information from the second device, the second device can pass the SLA information through the user network interface (User Network Interface, UNI) through multiple registration protocol (multiple registration protocol, MRP) message, local chain Link-local registration protocol (link-local registration protocol, LRP) message, network configuration protocol (Network Configuration Protocol, NETCONF) message, RESTCONF message or management information base (management information base, MIB) message, etc. are sent to the first device .

For example, as shown in FIG. 4 , the figure is a schematic diagram of a packet format carrying SLA information of a data flow provided by an embodiment of the present application. In the UserToNetworkRequirements TLV shown in Figure 4, the MaxLatency field carries the upper bound of the target latency, and the new field Latency_ConfidenceLevel carries the reliability probability. If the value of the Latency_ConfidenceLevel field is 999900, it means that the user accepts that in 99.99% of cases, the network guaranteed transmission delay is less than or equal to the upper bound of the target delay carried by MaxLatency. The device transmitting the data stream may register the data stream SLA information carried in the UserToNetworkRequirements TLV into a local MRP Data Unit (MRP Data Unit, MRPDU), and issue a declaration (declaration), and send it to the first device. The device transmitting the data stream may also register the data stream SLA information carried in the UserToNetworkRequirements TLV into the LRP database, and send a declaration to the first device.

Data flows belonging to different service types have different service requirements, and the corresponding SLA information is different. The SLA information may include the upper bound of the target latency, or may include the upper bound of the cache, or may include a combination of the upper bound of the target latency and the upper bound of the cache. Further, the SLA information may also include the reliability probability corresponding to the upper bound of the target latency, and the reliability probability of the cache upper bound.

The upper bound of the target delay, the upper bound of the cache, and the reliability probability in the embodiments of the present application are respectively introduced below:

The upper bound of the target delay is the maximum delay allowed by the transmitted data flow.

In a possible situation, the upper bound of the target delay may be the upper bound of the delay of transmitting the data flow from the source end to the destination end. The upper bound of the target delay can be the upper bound of the transmission delay of the entire network that transmits the data stream, or the upper bound of the transmission delay within the subnetwork that transmits the data stream. For example, when the source end is a device that generates data streams and the destination end is a device that receives data streams, the upper bound of the target delay represents the upper bound of the delay of data stream transmission in the network. When the source end and the destination end are respectively edge devices of a subnetwork, the upper bound of the target delay indicates the upper bound of the delay of data flow transmission in the subnetwork.

In another possible situation, the upper bound of the target delay may also be the upper bound of the delay of the data stream transmitted by the single-hop device transmitting the data stream. The upper bound of the target delay for transmitting data streams from the source to the destination is related to the upper bound of the target delay for transmitting data streams by a single device. For example, based on the number of devices transmitting data streams from the source end to the destination end and the upper bound of the target delay time for transmitting data streams from the source end end to the destination end, the upper bound of the target delay of data stream transmission by a single device can be obtained.

The cache upper bound indicates the minimum size of buffer available for the stream on the device including the shaper. The cache upper bound may be the smallest cache of queues supported by the device including the shaper.

The reliability probability indicates the probability of meeting the transmission requirement indicated by the SLA information corresponding to the data flow, for example, the reliability probability may be 99.99%. The reliability probability is related to the content of the SLA information. For example, when the SLA information of the data flow includes the upper bound of the target delay, the reliability probability of the upper bound of the target delay may also be included. The reliability probability of the upper bound of the target delay indicates the probability that the delay of the transmission data stream is less than or equal to the upper bound of the target delay. Specifically, for example, if the upper bound of the target delay is the upper bound of the delay of transmitting the data stream from the source to the destination, then the reliability probability is that the delay of transmitting the data stream from the source to the destination is less than or equal to the target The probability of an upper bound on the delay. If the upper bound of the target delay is the upper bound of the delay of the data stream transmitted by the single-hop device, then the reliability probability is the probability that the delay of the data stream transmitted by the single-hop device is less than or equal to the upper bound of the target delay. For another example, when the SLA information of the data flow includes the cache upper bound, the reliability probability indicates the probability that the available cache of the device including the shaper is less than or equal to the cache upper bound. In a possible implementation manner, the reliability probability p is a parameter greater than or equal to 0 and less than or equal to 1. When acquiring the delay violation probability/buffer overflow probability ε, the reliability probability p can be obtained through the relation p=1-ε, where ε is the maximum value of the violation probability. In a possible implementation manner, the reliability probability of the data flow transmitted from the source end to the destination end may be obtained according to the reliability probability of each device in the network. The calculation formula of the reliability probability p _k from the source end to the destination end of the transmission data stream is shown in formula (5):

p _k ＝1-(1-p) ^1/H (5)

Among them, p is the reliability probability of a single-hop device, and H is the number of devices transmitting data streams.

The first device determines the shaper parameter based on the acquired traffic collection information of the data flow and the SLA information corresponding to the data flow.

Wherein, the parameters of the shaper may be determined according to the type of the shaper. For example, for a shaper using the token bucket algorithm, the parameters of the shaper may include at least one of a token bucket depth (burst) and a token generation rate (rate). Among them, the bucket depth of the token bucket is also the committed burst size (committed burst size, CBS), and the token generation rate is also the committed information rate (committed information rate, CIR). For a credit based shaper (credit based shaper, CBS), the shaper parameters may include at least one of a credit accumulation rate (idleslope) and a credit consumption rate (sendslope).

In a possible implementation manner, the first device may first obtain the target bandwidth based on the acquired traffic collection information of the data flow and the SLA information corresponding to the data flow, and then use the target bandwidth to obtain the shaper parameters. Wherein, the target bandwidth is the minimum value of the available bandwidth for transmitting the data flow that satisfies the transmission requirement indicated by the SLA information. The embodiment of this application provides a specific calculation method of the target bandwidth, please refer to the following for details.

Regarding the token generation rate and the credit accumulation rate, in an implementation, the obtained value of the target bandwidth may be set as the value of the token generation rate or the credit accumulation rate. In another implementation, the target bandwidth may be multiplied by the protection coefficient, and the obtained value may be set as the value of the token generation rate or the credit accumulation rate. The protection factor can be 1.2, for example.

For the depth of the token bucket, in one implementation, the target bandwidth can be multiplied by the upper bound of the shaping delay to obtain the value of the token bucket depth. In another implementation, the value obtained by multiplying the target bandwidth by the upper bound of the shaping delay can be multiplied by the protection coefficient to obtain the value of the token bucket depth. Wherein, the upper bound of the shaping delay is the upper bound of the delay during the processing of the data flow in the shaper. The upper bound of the shaping delay can be determined based on the SLA information. For details, see the following.

For the credit consumption rate, in one implementation, the difference between the target bandwidth and the port transmission rate of the device including the shaper may be calculated, and the obtained value is set as the value of the credit consumption rate. In another implementation, the product of the target bandwidth and the protection coefficient may be calculated first, the difference between the obtained product and the port transmission rate may be calculated, and the obtained value may be set as the value of the credit consumption rate. Wherein, the port transmission rate is the rate at which the output port of the device including the shaper transmits the data flow.

According to the traffic collection information of the data flow and the SLA information corresponding to the data flow, different implementation methods of obtaining the target bandwidth are described below:

Manner 1: The first device first obtains the range of the target bandwidth according to the traffic collection information, and then determines the target bandwidth by using the SLA information.

The range of the target bandwidth is determined according to the traffic collection information, and is the value range of the minimum value of the available bandwidth for transmitting the data flow.

The embodiment of the present application provides two manners for determining the range of the target bandwidth.

In a possible implementation manner, the range of the target bandwidth may be determined by using the reference value and the correction value of the target bandwidth. The baseline value of the target bandwidth is determined based on traffic collection information. The correction value of the target bandwidth indicates the amount of fluctuation of the target bandwidth relative to the reference value.

Specifically, the reference value and correction value of the target bandwidth may be determined by using a time series processing method. For example, an n-order autoregressive method may be employed.

For example, taking n as 1 as an example, the embodiment of the present application provides an expression of the range α(θ) of the target bandwidth, as shown in formula (6).

Among them, α(θ) is a variable that has a mapping relationship with θ, and the specific value of α(θ) is determined by the value of θ. θ is the quality factor of SLA, which is used to measure the requirements of SLA in cache.

U ₁ is an average value of message lengths in multiple collection periods determined according to the traffic collection information. If the traffic collection information includes statistical values of packet lengths in multiple collection periods, and the statistical values include average values, the calculation of formula (6) can be performed directly using the average values in the traffic collection information. If the traffic collection information includes the lengths of packets in multiple collection periods, the average value can be calculated by using formula (1).

T is the total time of multiple collection cycles in the traffic collection information. v indicates the variance of the lengths of packets in multiple collection periods, which can be calculated by formula (7).

The covariance coefficient indicating the length of the packets in multiple collection periods can be calculated by formula (8).

v＝U ₂ −U ₁ *U ₁ (7)

Among them, U ₁ is the average value of the length of the message in multiple collection periods determined according to the traffic collection information, U ₂ is the second-order moment of the length of the message in multiple collection periods, and U ₃ is multiple collection periods The covariance of the lengths of the packets within . U ₁ , U ₂ and U ₃ can all be calculated according to the lengths of packets in multiple collection periods.

In another possible implementation manner, the traffic may be first fitted to a random distribution according to the traffic collection information and the distribution fitting algorithm, and then the range of the target bandwidth is determined according to the fitting result.

Specifically, the distribution fitting of the traffic may be realized through a distribution fitting algorithm. The distribution fitting algorithm can determine the random distribution that best matches the traffic distribution according to the traffic collection information. The random distribution may be one of random distributions such as Poisson distribution, composite Poisson distribution, Pareto distribution, Markov arrival process, or batch Markov arrival process.

Based on the determined traffic distribution, determine the value range of the target bandwidth. The expression of the value range α(θ) of the target bandwidth may be shown in formula (9).

α(θ)=log(exp(θX(T)))/θT (9)

Among them, α(θ) is a variable that has a mapping relationship with θ, the specific value of α(θ) is determined by the value of θ, and θ is the quality factor of SLA, which is used to measure the requirements of SLA in terms of caching. T is the total time of multiple collection cycles in the traffic collection information. X(T) is the distribution expectation determined based on the traffic distribution.

After the value range of the target bandwidth is determined, the target bandwidth is determined from the range of the target bandwidth based on the SLA information.

Taking the value range α(θ) of the above target bandwidth as an example, the target bandwidth can be determined by formula (10).

θ ^* α(θ ^* ) = -log(p)/D ₀ (10)

Among them, θ ^* is the quality factor of SLA, which is used to measure the requirement of SLA in terms of delay. There is a mapping relationship between θ ^* and θ. α(θ ^* ) can be obtained according to the mapping relationship between θ ^* and θ and α(θ). p can be a fixed value with a range of [0,1], or a reliability probability in the SLA information. D ₀ is the upper bound of the shaping delay, and the upper bound of the shaping delay is the upper bound of the delay during the processing of the data flow in the shaper. The upper bound of the shaping delay can be determined based on the SLA information. For details, see the following.

The specific value θ ₀ of θ ^* can be calculated by using formula (10), and then α(θ ₀ ) can be calculated to obtain the target bandwidth.

Method 2: The first device first obtains the burst volume of the data stream according to the traffic collection information, and then determines the target bandwidth by using the burst volume of the data stream and SLA information.

In this calculation method, the burst volume of the data stream may be determined based on the traffic collection information first. The burst amount is the length of the message corresponding to each acquisition period among the plurality of acquisition periods. In one implementation, the burst size may be the maximum burst size of the data stream. The maximum burst size of the data stream is the length of the message corresponding to the first cycle in multiple collection cycles, and the length of the message corresponding to the first cycle is the maximum length of the message corresponding to each collection cycle in multiple collection cycles value.

The target bandwidth R ₀ is calculated by using the burst volume of the data flow and the SLA information. For the specific calculation method, please refer to the formula (11).

R ₀ =B*p/D ₀ (11)

Wherein, B is the burst volume of the data flow. p can be a fixed value with a range of [0,1], or a reliability probability in the SLA information. D ₀ is the upper bound of the shaping delay, and the upper bound of the shaping delay is the upper bound of the delay during the processing of the data flow in the shaper. The upper bound of the shaping delay can be determined based on the SLA information. For details, see the following.

The above methods for calculating the target bandwidth are all based on the upper bound of the shaping delay. The following describes different implementations of determining the shaping delay according to the SLA information.

Case 1: The SLA information includes the upper bound of the target delay, and the target delay indicates the delay of data stream transmission in the network.

The upper bound of the target delay is the maximum delay required for the data flow to be transmitted in the network. It can be understood that there may be delays in various aspects during the process of transmitting data streams in the network, for example, shaping delays, fixed delays, network forwarding delays, and actual forwarding delays.

The shaping delay, fixed delay, network forwarding delay and actual forwarding delay are introduced below.

Wherein, the shaping delay indicates the delay during the processing of the data flow in the shaper. The shaping delay may include delays such as queuing delay of the device and preprocessing delay of the data flow, where the device is a device including a shaper. Wherein, for the shaper using the token bucket algorithm, the preprocessing delay may be the delay of processing the data stream before the data stream enters the token bucket. For a credit-based shaper, the pre-processing delay may be the delay of processing the data stream before determining the credit of the queue.

The fixed delay is a relatively definite delay generated by the network transmission data flow. The fixed delay may specifically include one or more of propagation delay, device processing delay, and port delay.

Among them, the propagation delay is the delay caused by the data stream propagating a certain distance in the transmission medium. Propagation delay indicates the ratio of transmission distance to transmission speed. Among them, the transmission speed is determined according to the type of the transmission signal and the propagation medium. For example, if the data flow is transmitted through the optical fiber line in the form of electromagnetic signals, then according to the propagation speed of the electromagnetic signal in the optical fiber line at 200,000 kilometers per second, it can be obtained that for an optical fiber line with a transmission distance of 1,000 kilometers, the The propagation delay is 5ms. Specifically, the propagation delay may be obtained by the first device during the service planning stage, or may be obtained through a telemetry (telemetry) technology, or may be obtained through other devices, such as a network controller (network controller).

The device processing delay is the delay caused by the device processing the data flow. The device processing delay may include the delay generated by the device performing, for example, analysis, data extraction, and routing search on the data stream after receiving the data stream. Device processing delay is an indicator parameter of the device. In an implementation, the device processing delay may be reported to the first device by the device transmitting the data stream, so that the first device determines the shaping delay according to the device processing delay. In another implementation, the device processing delay may also be pre-stored in the database of the first device, so that the first device acquires the device processing delay corresponding to the device transmitting the data stream from the database.

Port delay is the delay required by the device to send data streams. The port delay indicates the ratio of the packet length in the transmitted data flow to the port bandwidth. It can be understood that the port delay is determined according to the length of the packet transmitted by the port, and the port delay required for transmitting packets of different lengths is different. In a possible implementation manner, considering the range of the port delay, the maximum packet length in the data flow may be used to calculate the port delay.

The network forwarding delay is the preset delay for the data flow waiting to be processed in the forwarding device from the source end to the destination end. The network forwarding delay may be a preset queuing delay of the data flow in the forwarding device. Provide scheduling technology for network forwarding delay, for example, periodic queuing and forwarding (cyclic queuing) defined by Institute of Electrical and Electronics Engineers (IEEE) 802.1 Time Sensitive Network (TSN) Forwarding, CQF) or time awareness shaper (time awareness shaper, TAS) scheduling method, or QoS, hierarchical quality of service (hierarchical quality of service, HQoS), priority scheduling on routers and switches with reasonable configuration of queue parameters , Polling scheduling and other scheduling technologies.

In an implementation, the first device may obtain the network forwarding delay through a forwarding device that transmits the data flow. In another implementation, the first device may acquire and store the network forwarding delay in advance.

The network forwarding delay is related to the preset data flow waiting delay in each forwarding device.

In a possible implementation manner, the network forwarding delay may be determined according to the committed forwarding delay of each forwarding device. Wherein, the committed forwarding delay of the forwarding device is the preset delay of the data flow waiting for processing in the forwarding device. For example, the network forwarding delay D ₁ can be calculated by formula (12).

Among them, T _i is the committed forwarding delay T _i of each forwarding device that transmits data streams, i represents the number of forwarding devices, i is a positive integer less than or equal to M, and M is the total number of forwarding devices that transmit data streams.

In one scenario, the forwarding bandwidth of the forwarding device may be determined by using the committed forwarding delay T _i of the forwarding device. For example, the committed forwarding delay T _i of the forwarding device can be used as D ₀ in the above formula for calculating the target bandwidth, and the calculated target bandwidth R ₀ is the forwarding bandwidth of the forwarding device.

In another possible implementation manner, the forwarding capability of the forwarding device is measured by the preset forwarding bandwidth of the forwarding device. The committed forwarding delay of the forwarding device can be determined according to the preset forwarding bandwidth of the forwarding device, and then the network forwarding delay can be determined based on the committed forwarding delay.

The embodiment of the present application does not limit the manner of determining the committed forwarding delay according to the preset forwarding bandwidth of the forwarding device. In one implementation, the committed forwarding delay T _i can be calculated according to the deterministic network calculus algorithm, and the calculation method is shown in formula (13):

T _i =b/R _i (13)

Wherein, b is the token bucket bucket depth in the shaper parameter, or the committed burst size, and R _i is the preset forwarding bandwidth of the forwarding device.

The actual forwarding delay is the delay of the data flow waiting to be processed in the forwarding device from the source end to the destination end. The actual forwarding delay is the waiting delay generated in the forwarding device after the data stream is transmitted. The actual forwarding delay may be reported to the first device by the forwarding device transmitting the data stream after forwarding the data stream. The first device may obtain the actual forwarding delay from the source end to the destination end according to the forwarding delay reported by each forwarding device.

The delay included in the target delay is determined according to the network that transmits the data stream. The shaping delay is determined based on the delay in network transmission and the target delay.

The following describes different implementations of determining the shaping delay based on the target delay based on different scenarios.

Scenario 1: The target delay includes shaping delay.

In one implementation, the target delay may be determined as the shaping delay without considering the fixed delay, the network forwarding delay and the actual forwarding delay. For example, if the fixed delay from the source end to the destination end is relatively small and there is no forwarding device, the target delay may be determined as the shaping delay regardless of the fixed delay and the forwarding delay caused by the forwarding device.

For example, taking Figure 1 as an example, if the transmission from the sending end device 105 to the receiving end device 106 does not pass through other network devices, and the fixed delay is small and negligible, the upper bound of the target delay included in the SLA information can be determined and shaped The upper bound of the delay.

In another implementation, the upper bound of the target delay may be the delay of a single-hop device transmitting the data stream, and the target delay may be used as the shaping delay to calculate the forwarding bandwidth of the device.

Scenario 2: The target delay includes shaping delay, and also includes one or more of fixed delay and network forwarding delay.

In one implementation, one or more of fixed delay and network forwarding delay need to be considered. The shaping delay is obtained by subtracting one or more of the fixed delay and the network forwarding delay from the target delay.

For example, taking FIG. 1 as an example, if the upper bound of the target delay included in the SLA information is D=3ms, the propagation delay of the transmission data stream is 1.1ms, and the single device processing delay of the network devices 102-104 is 25 μs , The interface delay of a single device = maximum packet length / port bandwidth = 3.2μs. Then the upper bound of the fixed time delay is D _f =1.1 ms+25 μs×3+3.2 μs×3=1.1846 ms. If only the fixed delay is considered, then the upper bound of the shaped delay D ₀ =DD _f =1.8154ms.

If the single committed forwarding delay of the network devices 102-104 is 20 μs, then the network forwarding delay D _h =20 μs×3=0.06 ms. If only the network forwarding delay is considered, then the upper bound of the shaping delay D ₀ =DD _h =2.994ms.

If the target delay includes fixed delay and network forwarding delay, then the upper bound of shaping delay D ₀ =DD _f -D _h =1.7554ms.

Scenario 3: The target delay includes shaping delay, and also includes one or more of fixed delay and actual forwarding delay.

In one implementation, one or more of the fixed delay and the actual forwarding delay need to be considered. The shaping delay is obtained by subtracting one or more of the fixed delay and the actual forwarding delay from the target delay.

The calculation method of the upper bound of the shaping delay is similar to that of the upper bound of the shaping delay in Scenario 2, and will not be repeated here.

Case 2: The SLA information includes the buffer upper bound, and the buffer upper bound is the minimum value of the available buffer of the device including the shaper among the devices transmitting the data stream.

The cache upper bound has a mapping relationship with the target latency upper bound. In a possible implementation manner, the buffer upper bound may be converted into the upper bound of the target delay, and then the upper bound of the shaping delay may be determined by referring to the method in the first case above.

S304: The first device sends the shaper parameter to the third device.

Still taking FIG. 1 as an example, the first device is a control device 101, which is not a device for transmitting data streams, and the control device does not include a shaper for adjusting data streams. The first device sends the shaper parameter to the third device including the shaper, wherein the third device is a device including the shaper among the devices for transmitting data streams.

Referring to FIG. 1 , the third device may be the network devices 102 - 104 in FIG. 1 or the sending end device 105 .

In an example, the first device sends the shaper parameter to the third device through a committed information rate of a scheduler instance (scheduler instance) of NETCONF/YANG or RESTCONF/YANG.

The second device that collects traffic collection information of the data stream may be the same device as the third device that includes the shaper. For example, still taking FIG. 1 as an example, the network device 102 may be a second device that collects traffic collection information of data streams, and the network device 102 may also be a third device including a shaper. The first device, namely the control device 101 , obtains traffic collection information from the network device 102 and sends shaper parameters to the network device 102 . The second device that collects traffic collection information of the data stream may be different from the third device that includes shaping. Still taking FIG. 1 as an example, the network device 102 may be a second device that collects traffic collection information of data streams, and the network device 103 is a third device including a shaper. The first device, that is, the control device 101 obtains traffic collection information from the network device 102 and sends shaper parameters to the network device 103 .

S305: The third device configures the shaper according to the shaper parameter.

The third device configures the shaper by using the received shaper parameters. The configured shaper is used to shape the data flow, so that the transmission of the data flow adjusted by the shaper can meet the transmission requirements indicated by the SLA information.

Through the above method, the first device can obtain the shaper parameters corresponding to the SLA information of the data flow according to the flow collection information of the data flow and the SLA information corresponding to the data flow, and can more accurately shape the data flow through the shaper Processing, so that the processed data flow meets the transmission requirements indicated by the SLA information. Based on the traffic collection information of the data flow, the parameters of the shaper can be more accurately and flexibly matched with the service requirements corresponding to the data flow, and the differentiated guarantee for the service requirements of the data flow of different service types can be realized.

After the data flow is adjusted by the shaper, there is still a situation that the transmission of the data flow cannot meet the transmission requirements indicated by the SLA information. The following is an introduction to possible abnormalities in network transmission and corresponding adjustment methods.

Case 1: The congestion degree of the network is greater than the threshold.

The forwarding device that transmits the data stream has a preset buffer capacity, which is used to ensure that the actual forwarding delay of the forwarding device forwarding the data stream is less than or equal to the promised forwarding delay. The forwarding device can control network congestion by adjusting the occupied preset buffer capacity.

The degree of congestion of the network may be determined according to the remaining capacity of the forwarding equipment transmitting the data flow. Wherein, the remaining capacity is used to represent the remaining forwarding capability of the forwarding device when the committed forwarding delay of the forwarding device is guaranteed. The remaining capacity of the forwarding device may specifically be the unused preset buffer capacity of the forwarding device, which may be obtained by subtracting the burst amount of the data flow from the preset buffer capacity of the forwarding device.

In an implementation, each forwarding device may report the remaining capacity corresponding to each forwarding device to the first device. The first device determines the congestion degree of the network according to the obtained remaining capacity of each forwarding device. In a possible implementation manner, the first device may determine the congestion degree according to the remaining capacity of each forwarding device. In another possible implementation manner, the first device may determine the bottleneck device according to the remaining capacity of each forwarding device. The bottleneck device is the forwarding device with the smallest remaining capacity. The first device may determine the degree of congestion according to the remaining capacity of the bottleneck device, and may also adjust the weight used when determining the degree of congestion based on the remaining capacity of the bottleneck device.

When the congestion degree of the network is greater than the threshold, it indicates that the congestion degree of the network may not meet the requirement of the congestion degree of data stream transmission. The transmission mode of the data flow may be further adjusted, so that the adjusted data flow can meet the transmission requirement indicated by the SLA information and the congestion degree is less than or equal to the threshold.

The embodiment of the present application provides three possible methods for adjusting data stream transmission, one or more of which may be used to adjust the data stream transmission, specifically including:

Manner 1: The first device adjusts the SLA information, re-determines the shaper parameters based on the adjusted SLA information, and adjusts the data flow.

The first device may adjust the composition of the upper bound of the target delay or the upper bound of the cache included in the SLA information, so as to adjust the parameters of the shaper.

Taking the target delay as an example, the target delay may include shaping delay and network forwarding delay. The network forwarding delay may have a certain value range. The first device can adjust the network forwarding delay, so as to realize the adjustment of the shaping delay, and then adjust the parameters of the shaper, so as to realize the adjustment of the data flow.

The first device may adjust the distribution ratio of the shaping delay and the network forwarding delay. In a possible implementation manner, the proportion of the shaping delay and the network forwarding delay may be randomly determined within a certain proportion range. In another possible implementation manner, the adjustment step size may be increased for the shaping delay, and the adjustment step size may be decreased for the network forwarding delay. The adjustment step size can be determined according to the congestion degree of the network, and the adjustment step size can be a positive number or a negative number.

The first device then uses the adjusted shaping delay to calculate and obtain adjusted shaper parameters. The second device may configure the shaper with the adjusted shaper parameters.

In addition, after determining the adjusted network forwarding delay, the first device may calculate the committed forwarding delay corresponding to each forwarding device, or calculate the forwarding bandwidth corresponding to each forwarding device. The first device sends the re-determined committed forwarding delay or forwarding bandwidth of the forwarding device to each forwarding device, so that each forwarding device adjusts the committed forwarding delay or forwarding bandwidth.

In one implementation, if the new shaper parameters are determined based on the adjusted SLA information, and the data flow is adjusted, the congestion degree of the network is still greater than the threshold, and the SLA information can be adjusted again to continue to generate the corresponding The shaper parameter adjusts the data flow until the times of adjusting the SLA information reaches the adjustment threshold, or the congestion degree is less than or equal to the threshold.

Manner 2: The first device adjusts the queue into which the data flow enters.

The first device may adjust the queues into which the data streams enter, and re-divide the queues into which the data streams enter, so that the adjusted data streams can meet the transmission requirements indicated by the SLA information and the congestion degree is less than or equal to the threshold.

Similarly, in one implementation, if the adjusted data flow still has a network congestion level greater than the threshold during transmission, the queue into which the data flow enters can be divided again, and the congestion level can be re-determined until the adjustment The number of times the data flow enters the queue reaches the adjustment threshold, or until the degree of congestion is less than or equal to the threshold.

Manner 3: The first device adjusts the transmission path of the data stream.

The first device may also adjust the transmission path of the transmission data stream. Re-determine the transmission path of the data flow by adjusting the equipment that transmits the data flow.

The first device obtains a transmission path of the data stream through multiprotocol label switching (multiprotocol label switching, MPLS) or traffic engineering (traffic engineering, TE) technology, and determines a device for transmitting the data stream on the transmission path. After the first device determines the device on the path for transmitting the data stream, it can obtain network status information and device capability information based on the network configuration protocol (network configuration protocol, NETCONF) or representational state transfer configuration protocol (representational state transfer configuration protocol, RESTCONF) , such as obtaining the port rate, the maximum available bandwidth of the link, the maximum remaining bandwidth of the link, the weight of the link, the maximum transmission unit (MTU) of the link, the scheduling method and parameters of the device, and the processing time of the device Delay, device cache capability and other information. For example, the first device acquires network status information and device capability information through NETCONF/YANG or RESTCONF/YANG. It should be understood that the first device may deploy network resources according to the foregoing network status information and device capability information.

Similarly, in one implementation, if the data flow after the transmission path is adjusted still has a network congestion degree greater than a threshold during transmission, the transmission path of the data flow can be adjusted again, and the congestion degree can be re-determined. Until the number of times of adjusting the transmission path of the data flow reaches the adjustment threshold, or the degree of congestion is less than or equal to the threshold.

Situation 2: The time delay for transmitting the data flow from the source end to the destination end, or the estimated value of the time delay for transmitting the data flow from the source end end to the destination end does not meet the transmission requirement of the upper bound of the target time delay in the SLA information.

When the data flow is transmitted, the data flow may also be divided into queues, diverted, and converged with other data flows, resulting in the expected transmission process of one or more data flows, or the actual transmission process. The transmission requirements indicated by the SLA information corresponding to the data flow are met.

Taking the SLA information including the upper bound of the target delay as an example, in one implementation, after the data stream adjusted by the shaper arrives at the destination, the measured actual transmission delay from the source to the destination may be greater than The upper bound of the target delay; in another implementation, the estimated value of the delay of the data flow from the source end to the destination end calculated by the network management device according to the planned transmission path of the data flow is greater than the upper bound of the target delay. Wherein, the network management device may be a device including a path computation element (path computation element, PCE), or may be a device connected to the PCE.

Based on such situations, the transmission of the data flow needs to be adjusted. Similarly, one or more of the above three methods for adjusting data stream transmission may be used, so that the adjusted data stream meets the transmission requirements of the SLA information.

Based on the above content, it can be seen that by determining the congestion degree of the network, or the delay of the network transmission data flow or the estimated value of the delay of the network transmission data flow, it can be judged whether the network transmission data flow can meet the transmission requirements of the data flow. When the transmission data flow does not meet or may not meet the transmission requirements, the transmission of the data flow is adjusted so that the transmission of the data flow meets the transmission requirements.

In the foregoing implementation manner, the first device is an independent control device. In addition, the first device can also be a device with an integrated control function. With reference to the schematic diagram of the network architecture shown in FIG. indivual.

In an implementation, the first device with a control function may acquire traffic collection information of the data flow, and configure shaper parameters for a shaper included in itself. For example, as shown in FIG. 5 , the sending end device 105 or the network devices 102-104 can acquire the traffic collection information of the data flow, obtain the shaper parameters based on the traffic collection information of the data flow and the SLA information corresponding to the data flow, and The shaper included with the device is configured.

Referring to Figure 5, this figure is a schematic flowchart of a network configuration method provided in the embodiment of the present application, specifically including:

S501: The first device acquires traffic collection information of a data stream.

The first device collects traffic on the transmitted data stream to obtain traffic collection information. For the traffic collection information of the data stream, refer to the description in S301, and details are not repeated here.

S502: The first device determines shaper parameters according to traffic collection information and SLA information corresponding to the data flow.

For the method for the first device to determine the shaper parameter, reference may be made to the description of the method for determining the shaper parameter in S303, and details are not repeated here.

S503: The first device configures the shaper according to the shaper parameter.

Based on the determined shaper parameters, the first device configures shaper parameters for the included shaper, so that the shaper after the shaper parameter configuration can adjust the data flow to meet the transmission indicated by the SLA information corresponding to the data flow Require.

In another implementation, the first device with a control function may obtain traffic collection information of the data flow through other devices, and send the obtained shaper parameters to other devices including the shaper. Wherein, the traffic collection information of the data flow and the shaper parameters may be sent to the first device through the transmission path of the transmission data flow.

For example, as shown in FIG. 2, the first device may be the receiving end device 106, and the network device 102 may obtain the flow collection information of the data flow, and send the flow collection information of the data flow to the receiving end device through the network devices 103 and 104 106. After obtaining the shaper parameters, the receiver device 106 sends the shaper parameters to the network device 102 including the shaper, so that the network device 102 configures the shaper parameters for the shaper.

For this type of implementation, the interaction process between devices can refer to the schematic diagram of interaction of the network configuration method shown in FIG. 3 , which will not be repeated here.

In a possible implementation manner, the second device may be the same device as the first device. The first device collects traffic collection information of the data flow, determines shaper parameters based on the traffic collection information, and sends the shaper parameters to a third device including the shaper, so that the third device uses the shaper parameters to configure the shaper, and the data flow Carry out shaping. For example, the first device may be the sink device 106 . The first device may collect data streams, obtain traffic collection information, obtain shaper parameters, and send the shaper parameters to the third device, that is, the network device 102 . The network device 102 configures the shaper with shaper parameters, so that the shaper processes the data flow.

In another possible implementation manner, the third device may be the same device as the first device. The second device collects traffic collection information of the data stream, determines shaper parameters based on the traffic collection information, and uses the shaper parameters to adjust the shaper included in the first device. For example, the second device may be the sending end device 105 , and the first device may be the network device 102 . The second device may collect the data flow to obtain flow collection information. The second device sends the traffic collection information to the first device, that is, the network device 102 . The network device 102 obtains the shaper parameters according to the traffic collection information and the SLA information corresponding to the data flow. The network device 102 configures the shaper using the obtained shaper parameters.

For the third scenario above, the target delay includes the shaping delay, and also includes one or more of the fixed delay and the actual forwarding delay. In this implementation, the actual forwarding delay can be the , sending the forwarding delay to the first device. For example, as shown in FIG. 2 , the first device is the receiving end device 106 . After the network device 102 forwards the data flow, the actual device forwarding delay of the network device 102 is sent to the receiving end device 106 through the network devices 103 and 104 . Similarly, after the network devices 103 and 104 forward the data flow, the actual device forwarding delay of the device is sent to the receiving end device 106 through the network device through the transmission path of the subsequent data flow. The receiver device 106 determines the actual forwarding delay based on the forwarding delay sent by the network devices 102-104.

In addition, the embodiment of the present application also provides a situation in which the first device is a device with an integrated control function, an abnormal situation that may occur in network transmission and a corresponding adjustment method. The following is an introduction to possible abnormalities in network transmission and corresponding adjustment methods.

Case 1: The congestion degree of the network is greater than the threshold.

For this kind of situation, the method for determining the degree of network congestion and the method for adjusting it are similar to the first case above, that is, the method for the degree of network congestion is greater than the threshold, please refer to the above description, and will not repeat them here.

In such an implementation manner, the remaining capacity of the forwarding device may be transmitted to the first device through a transmission path for transmitting data streams. Taking the receiving end device 106 in FIG. 2 as the first device as an example, the method for the first device to obtain the remaining capacity of the forwarding device will be described below.

Referring to FIG. 2 as an example, the forwarding devices are network devices 102-104. Each forwarding device can obtain the remaining capacity according to the burst amount when transmitting the data stream and the preset buffer capacity of the forwarding device. For example, the preset buffer capacity of each forwarding device is C _x , where x is the number of forwarding devices. The burst size when the forwarding device transmits the data flow is b _x , please refer to formula (14).

b _x =b _x-1 +rT _x (14)

Wherein, r is the output bandwidth of the data stream output by the shaper, and T _x is the actual forwarding delay of the forwarding device. When the value of x is 1, b ₀ is the minimum value of the available cache of the shaper.

Each forwarding device can obtain the remaining capacity C _x ′ according to the burst amount of the transmission data flow and the preset buffer capacity. For the calculation method of C _x ', please refer to formula (15).

C _x '＝C _x -b _x (15)

The forwarding device sends one or more of the burst b _x and the remaining capacity C _x ′ to the receiving end device 106 through the transmission path of the transmission data flow. The receiving end device 106 may determine whether the congestion degree of the network is greater than a threshold according to the obtained remaining capacity of each forwarding device.

Situation 2: The time delay for transmitting the data stream from the source end to the destination end, or the estimated value of the time delay for transmitting the data stream from the source end to the destination end does not meet the transmission requirement of the SLA information.

For such cases, the method of determining the delay or the estimated value of the delay and the adjustment method are the same as the second case above, that is, the delay of transmitting the data flow from the source to the destination, or the time of transmitting the data flow from the source to the destination. The method in which the estimated value of delay does not meet the transmission requirement of the SLA information is similar, please refer to the above description, and will not repeat it here.

Through the above implementation method, the first device can obtain the shaper parameters corresponding to the data flow and the SLA information of the data flow according to the traffic collection information of the data flow and the SLA information corresponding to the data flow, and can achieve more accurate data flow through the shaper. The data flow is shaped so that the processed data flow meets the transmission requirements indicated by the SLA information. Based on the traffic collection information of the data flow, the parameters of the shaper can be more accurately and flexibly matched with the service requirements corresponding to the data flow, and the differentiated guarantee for the service requirements of the data flow of different service types can be realized.

FIG. 6 is a schematic structural diagram of a first device 1000 according to an embodiment of the present application. The first device 1000 shown in FIG. 6 may execute corresponding steps performed by the first device in the method of the foregoing embodiments. The first device is deployed in a communications network that also includes a second device. As shown in FIG. 6 , the first device 1000 includes an acquiring unit 1001 and a processing unit 1002 .

An acquisition unit 1001, configured to acquire traffic collection information of the data stream;

The processing unit 1002 is configured to determine shaper parameters according to traffic collection information and SLA information corresponding to the data flow; the shaper parameters are used by the shaper to adjust the data flow to meet the transmission requirements indicated by the SLA information.

Optionally, the processing unit 1002 is specifically configured to:

Obtain the target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow; the target bandwidth is the minimum value of the available bandwidth used to transmit the data flow to meet the transmission requirements indicated by the SLA information;

Determine the shaper parameters based on the target bandwidth.

Optionally, when the processing unit 1002 obtains the target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow, the processing unit 1002 is specifically configured to:

Obtain the range of the target bandwidth according to the traffic collection information;

The target bandwidth is obtained according to the range of the target bandwidth and the SLA information corresponding to the data flow.

Optionally, in the scope where the processing unit 1002 obtains the target bandwidth according to the traffic collection information, the processing unit 1002 is specifically configured to:

The range of the target bandwidth is determined according to the reference value and the correction value; the reference value is the reference value of the target bandwidth determined according to the traffic collection information, and the correction value indicates the fluctuation amount of the target bandwidth relative to the reference value.

Optionally, the range in which the processing unit 1002 obtains the target bandwidth according to the traffic collection information includes:

The first device determines the range of the target bandwidth according to the distribution fitting algorithm and the traffic collection information.

Optionally, the traffic collection information includes the length of the packets of the data stream in multiple collection periods; when the processing unit 1002 obtains the target bandwidth according to the traffic collection information and the SLA information corresponding to the data stream, the processing unit 1002 is specifically used for:

Obtain the burst volume of the data flow according to the traffic collection information; the burst volume is the length of the message corresponding to each collection cycle in multiple collection cycles;

Calculate the target bandwidth based on the burst size and the SLA information corresponding to the data flow.

Optionally, the first device also includes:

The first adjustment unit is configured to adjust the SLA information in response to the congestion degree being greater than the threshold, so that the data flow is adjusted according to the shaper parameters determined according to the adjusted SLA information and the traffic collection information, so as to meet the transmission requirements indicated by the SLA information and The degree of congestion is less than or equal to the threshold;

and / or,

Adjust the queue that the data flow enters to meet the transmission requirements indicated by the SLA information and the congestion degree is less than or equal to the threshold;

and / or,

Adjusting the transmission path of the data stream, so that the data stream transmitted through the transmission path meets the transmission requirements indicated by the SLA information and the degree of congestion is less than or equal to the threshold;

Among them, the degree of congestion is determined according to the remaining capacity of the forwarding equipment, and the remaining capacity refers to the remaining forwarding capability of the forwarding equipment under the guaranteed forwarding delay of the forwarding equipment. delay.

Optionally, the first device also includes:

The second adjustment unit adjusts the SLA information in response to the time delay of transmitting the data flow from the source end to the destination end, or the estimated value of the time delay of transmitting the data flow from the source end to the destination end does not meet the transmission requirements of the SLA information, so that Adjust the data flow according to the adjusted SLA information and the shaper parameters determined by the traffic collection information, so as to meet the transmission requirements indicated by the SLA information;

and / or,

Adjust the queue that the data flow enters to meet the transmission requirements indicated by the SLA information;

and / or,

The transmission path of the data flow is adjusted so that the data flow transmitted through the transmission path meets the transmission requirements indicated by the SLA information.

Optionally, the SLA information includes the upper bound of the target delay; the upper bound of the target delay indicates the upper bound of the delay of the data flow from the source end to the destination end.

Optionally, the target delay includes a shaping delay; the shaping delay indicates a delay during processing of the data flow in the shaper.

Optionally, the target delay also includes one or more of fixed delay and network forwarding delay; fixed delay includes one or more of propagation delay, device processing delay and port delay; Latency is the delay of data flow propagating in the transmission medium; device processing delay is the delay of equipment processing data flow; port transmission delay is the delay of transmitting data flow through the port; network forwarding delay is from source to At the destination end, the preset delay for data streams to wait for processing in the forwarding device.

Optionally, the network forwarding delay indicates the sum of committed forwarding delays of multiple forwarding devices transmitting data streams; the committed forwarding delay is a preset delay for data streams waiting to be processed in the forwarding devices.

Optionally, the network forwarding delay is determined according to preset forwarding bandwidths of multiple forwarding devices transmitting data streams; the preset forwarding bandwidth is the preset bandwidth of data streams forwarded by the forwarding devices.

Optionally, the target delay also includes one or more of fixed delay and actual forwarding delay;

The actual forwarding delay indicates the delay of the data flow waiting to be processed in the forwarding device from the source end to the destination end.

Optionally, the SLA information includes a cache upper bound; the cache upper bound is a minimum value of an available cache of a device including a shaper among devices transmitting data streams.

Optionally, the acquiring unit 1001 is specifically used for:

The flow collection information of the data flow sent by the second device is received; the second device is a device for transmitting the data flow.

Optionally, the acquiring unit 1001 is specifically used for:

The flow collection information of the data flow collected by the first device is acquired.

Optionally, the traffic collection information includes the statistical value of the length of the packets of the data flow in multiple collection periods; the statistical value includes an average value, and the average value indicates the length of multiple packets in the collected data flow and is related to the length of multiple packets collected in the data flow. The ratio of the number of collection cycles experienced by the packet.

Optionally, the statistical value also includes one or more of the second-order moment and the fourth-order moment; the second-order moment indicates that the sum of the squares of the lengths of the multiple packets in the collected data stream is equal to the sum of the lengths of the multiple packets collected. The ratio of the number of acquisition cycles experienced; the fourth moment indicates the ratio of the sum of the fourth powers of the lengths of the plurality of packets in the acquisition data stream to the number of acquisition cycles experienced by the acquisition of the plurality of packets.

Optionally, the first device also includes:

A sending unit, configured to send the shaper parameters to a third device; the third device is a device for transmitting data streams including the shaper.

Optionally, the control device is a central network control CNC device.

FIG. 7 is a schematic diagram of a hardware structure of a first device 1100 according to an embodiment of the present application. The first device 1100 shown in FIG. 7 may execute corresponding steps performed by the first device in the method of the foregoing embodiments.

As shown in FIG. 7 , the first device 1100 includes a processor 1101 , a memory 1102 , an interface 1103 and a bus 1104 . The interface 1103 can be implemented in a wireless or wired manner, specifically, it can be a network card. The aforementioned processor 1101 , memory 1102 and interface 1103 are connected through a bus 1104 .

The interface 1103 may specifically include a transmitter and a receiver for sending and receiving information between the first device and the second device in the above embodiment, and between the first device and the third device in the above embodiment. For example, the interface 1103 is configured to support receiving a traffic collection message sent by the second device. For another example, the interface 1103 is used to support the first device to send the shaper parameter to the third device. As an example, the interface 1103 is used to support the processes S302 and S304 in FIG. 3 . The processor 1101 is configured to execute the processing performed by the first device in the foregoing embodiments. For example, the processor 1101 is configured to determine shaper parameters according to traffic collection information and SLA information corresponding to the data flow; and/or other processes used in the technologies described herein. As an example, the processor 1101 is used to support the process S303 in Fig. 3 . The memory 1102 includes an operating system 11021 and an application program 11022 for storing programs, codes or instructions. When the processor or hardware device executes these programs, codes or instructions, the processing process related to the first device in the method embodiment can be completed. Optionally, the memory 1102 may include a read-only memory (English: Read-only Memory, abbreviated: ROM) and a random access memory (English: Random Access Memory, abbreviated: RAM). Among them, ROM includes basic input/output system (English: Basic Input/Output System, abbreviation: BIOS) or embedded system; RAM includes application program and operating system. When it is necessary to run the first device 1100, the BIOS solidified in the ROM or the bootloader in the embedded system is used to boot the system, and guide the first device 1100 into a normal running state. After the first device 1100 enters the normal running state, the application program and the operating system in the RAM are run, thereby completing the processing procedures related to the first device in the method embodiment.

It can be understood that FIG. 7 only shows a simplified design of the first device 1100 . In practical applications, the first device may include any number of interfaces, processors or memories.

FIG. 8 is a schematic diagram of a hardware structure of another first device 1200 according to an embodiment of the present application. The first device 1200 shown in FIG. 8 may execute corresponding steps performed by the first device in the method of the foregoing embodiments.

As shown in FIG. 8 , the first device 1200 includes: a main control board 1210 , an interface board 1230 , a switching fabric board 1220 , and an interface board 1240 . The main control board 1210, the interface boards 1230 and 1240, and the switching fabric board 1220 are connected to the system backplane through the system bus to realize intercommunication. Among them, the main control board 1210 is used to complete functions such as system management, equipment maintenance, and protocol processing. The SFU 1220 is used to implement data exchange between interface boards (interface boards are also called line cards or service boards). The interface boards 1230 and 1240 are used to provide various service interfaces (for example, POS interface, GE interface, ATM interface, etc.), and realize data packet forwarding.

The interface board 1230 may include a central processing unit 1231 , a forwarding entry storage 1234 , a physical interface card 1233 and a network processor 1232 . Wherein, the central processing unit 1231 is used for controlling and managing the interface board and communicating with the central processing unit on the main control board. The forwarding entry storage 1234 is used for storing forwarding entries. The physical interface card 1233 is used to receive and send traffic. The network storage 1232 is used to control the physical interface card 1233 to send and receive traffic according to the forwarding entry.

Specifically, the physical interface card 1233 may be used to receive traffic collection information sent by the second device. The physical interface card 1233 may also be used to send shaper parameters to the third device.

The physical interface card 1233 receives the flow collection information, and sends the flow collection information to the central processing unit 1211 via the central processing unit 1231, and the central processing unit 1211 processes the flow collection information.

The central processing unit 1211 is further configured to determine shaper parameters according to traffic collection information and SLA information corresponding to the data flow.

The central processor 1231 is also used to control the network storage 1232 to obtain the forwarding entry in the forwarding entry storage 1234, and the central processing unit 1231 can also be used to control the network storage 1232 to send the shaper parameters to the third device via the physical interface card 1233 .

It should be understood that the operations on the interface board 1240 in this embodiment of the present invention are consistent with the operations on the interface board 1230 , and are not repeated for brevity. It should be understood that the first device 1200 in this embodiment may correspond to the functions and/or various steps implemented in the foregoing method embodiments, and details are not repeated here.

In addition, it should be noted that there may be one or more main control boards, and when there are multiple main control boards, the main main control board and the standby main control board may be included. There may be one or more interface boards, and the stronger the data processing capability of the first device, the more interface boards it provides. There may also be one or more physical interface cards on the interface board. There may be no SFU, or there may be one or more SFUs. When there are multiple SFUs, they can jointly implement load sharing and redundant backup. Under the centralized forwarding architecture, the first device may not need a switching network board, and the interface board is responsible for processing service data of the entire system. Under the distributed forwarding architecture, the first device may have at least one SFU, through which data exchange between multiple interface boards is implemented, and large-capacity data exchange and processing capabilities are provided. Therefore, the data access and processing capabilities of the first device in the distributed architecture are greater than those in the centralized architecture. Which architecture to use depends on the specific networking deployment scenario, and there is no limitation here.

In addition, an embodiment of the present application provides a computer storage medium for storing computer software instructions used by the above-mentioned first device, which includes the program designed for executing the above-mentioned method embodiment.

The embodiment of the present application also includes a network system, the network system includes a first device and a second device,

The second device is configured to send traffic collection information of the data stream to the first device;

The first device is configured to receive traffic collection information of the data stream sent by the second device;

The first device is further configured to determine shaper parameters according to traffic collection information and SLA information corresponding to the data flow; the shaper parameters are used by the shaper to adjust the data flow to meet the transmission requirements indicated by the SLA information.

In a possible implementation manner, the network system further includes a third device,

The first device is further configured to send the shaper parameter to the third device;

The third device is configured to receive the shaper parameters sent by the first device, and configure the shaper according to the shaper parameters; the third device is a device for transmitting data streams including the shaper.

Wherein, the first device may be the first device in the aforementioned FIG. 6 or FIG. 7 or FIG. 8 , and realize any function described in the foregoing embodiments.

The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical business division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

A unit described as a separate component may or may not be physically separated, and a component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each business unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software business units.

If the integrated unit is realized in the form of a software business unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .

Those skilled in the art should be aware that, in one or more examples above, the services described in the present invention may be implemented by hardware, software, firmware or any combination thereof. When implemented in software, the services 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.

The above specific implementation manners have further described the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation manners of the present invention.

Above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be applied to the foregoing embodiments The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the application.

Claims

A network configuration method, characterized in that the method comprises:

The first device acquires traffic collection information of the data stream;

The first device determines shaper parameters according to the traffic collection information and service level agreement (SLA) information corresponding to the data flow; the shaper parameters are used by the shaper to adjust the data flow to meet the The transmission requirements indicated by the SLA information.
The method according to claim 1, wherein the first device determines shaper parameters according to the traffic collection information and the SLA information corresponding to the data flow, including:

The first device obtains a target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow; the target bandwidth is an available bandwidth that satisfies the transmission requirements indicated by the SLA information and is used to transmit the data flow The minimum value of the bandwidth;

The first device determines the shaper parameters according to the target bandwidth.
The method according to claim 2, wherein the first device obtains the target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow, including:

The first device obtains the range of the target bandwidth according to the traffic collection information;

The first device obtains the target bandwidth according to the range of the target bandwidth and SLA information corresponding to the data flow.
The method according to claim 3, wherein the first device obtains the range of the target bandwidth according to the traffic collection information, including:

The first device determines the range of the target bandwidth according to a reference value and a correction value; the reference value is a reference value of the target bandwidth determined according to the traffic collection information, and the correction value indicates that the target bandwidth is relatively The amount of fluctuation from the base value.
The method according to claim 3, wherein the first device obtains the range of the target bandwidth according to the traffic collection information, including:

The first device determines the range of the target bandwidth according to a distribution fitting algorithm and the traffic collection information.
The method according to claim 2, wherein the flow collection information includes the length of the packets of the data flow in multiple collection periods; the first device according to the flow collection information and the The SLA information corresponding to the data flow obtains the target bandwidth, including:

The first device acquires the burst amount of the data stream according to the traffic collection information; the burst amount is the length of the message corresponding to each collection cycle among the multiple collection cycles;

The first device calculates the target bandwidth according to the burst amount and SLA information corresponding to the data flow.
The method according to any one of claims 1-6, wherein, in response to the degree of congestion being greater than a threshold, the method further comprises:

The first device adjusts the SLA information, so that the data flow is adjusted according to the adjusted SLA information and the shaper parameters determined by the traffic collection information, so as to meet the transmission requirements indicated by the SLA information, and the The congestion level is less than or equal to the threshold;

and / or,

The first device adjusts the queue into which the data flow enters, so as to meet the transmission requirement indicated by the SLA information and the congestion degree is less than or equal to the threshold;

and / or,

The first device adjusts the transmission path of the data flow, so that the transmission of the data flow through the transmission path meets the transmission requirements indicated by the SLA information and the congestion degree is less than or equal to the threshold;

Wherein, the congestion degree is determined according to the remaining capacity of the forwarding device, and the remaining capacity refers to the remaining forwarding capability of the forwarding device when the committed forwarding delay of the forwarding device is guaranteed, and the committed forwarding delay is the A preset time delay for data streams to wait for processing in the forwarding device.
The method according to any one of claims 1-6, characterized in that, in response to the delay in transmitting the data flow from the source end to the destination end, or the delay in transmitting the data flow from the source end end to the destination end The estimated value of does not meet the transmission requirements of the SLA information, and the method further includes:

The first device adjusts the SLA information, so that the data flow is adjusted according to the adjusted SLA information and the shaper parameters determined by the traffic collection information, so as to meet the transmission requirements indicated by the SLA information;

and / or,

The first device adjusts the queue into which the data flow enters, so as to meet the transmission requirements indicated by the SLA information;

and / or,

The first device adjusts the transmission path of the data flow, so that the transmission of the data flow through the transmission path meets the transmission requirement indicated by the SLA information.
The method according to any one of claims 1-8, wherein the SLA information includes an upper bound of a target delay; the upper bound of the target delay indicates the time it takes for the data stream to travel from the source end to the destination end. Extended upper bound.
The method according to claim 9, wherein the target delay includes a shaping delay; the shaping delay indicates a delay during processing of the data flow in the shaper.
The method according to claim 10, wherein the target delay further includes one or more of fixed delay and network forwarding delay; the fixed delay includes propagation delay, device processing delay and port delay; the propagation delay is the delay of the data flow propagating in the transmission medium; the device processing delay is the delay of the device processing the data flow; the The port transmission delay is the delay of transmitting the data flow through the port; the network forwarding delay is the preset time for the data flow to be processed in the forwarding device from the source end to the destination end delay.
The method according to claim 11, wherein the network forwarding delay indicates the sum of committed forwarding delays of multiple forwarding devices transmitting the data stream; the committed forwarding delay is the data A preset delay for a stream to wait for processing in the forwarding device.
The method according to claim 11, wherein the network forwarding delay is determined according to the preset forwarding bandwidth of a plurality of forwarding devices transmitting the data stream; the preset forwarding bandwidth is the forwarding device A preset bandwidth for forwarding the data flow.
The method according to claim 10, wherein the target delay further includes one or more of a fixed delay and an actual forwarding delay;

The actual forwarding delay indicates the delay of the data flow waiting to be processed in the forwarding device from the source end to the destination end.
The method according to any one of claims 1-8, wherein the SLA information includes a cache upper bound; the cache upper bound is an available cache of a device including a shaper among devices transmitting the data stream minimum value.
The method according to any one of claims 9-15, wherein the SLA information further includes a reliability probability, and the reliability probability is a probability of meeting a transmission requirement indicated by the SLA information corresponding to the data flow.
The method according to any one of claims 1-16, wherein the acquisition of the flow collection information of the data flow by the first device includes:

The first device receives the traffic collection information of the data stream sent by the second device; the second device is a device for transmitting the data stream.
The method according to claim 17, wherein the traffic collection information includes the statistical value of the length of the packets of the data flow in multiple collection periods; the statistical value includes an average value, and the average value Indicates the ratio of the lengths of the multiple packets in the data stream collected to the number of collection cycles experienced in collecting the multiple packets.
The method according to any one of claims 1-18, wherein the method further comprises:

The first device sends the shaper parameters to a third device; the third device is a device that includes a shaper and transmits the data stream.
The method according to any one of claims 1-19, wherein the first device is a control device or a device transmitting the data stream.
The method according to claim 20, wherein the control device is a central network control CNC device.
The method according to any one of claims 1-21, wherein the shaper parameters include at least one of token bucket depth and token generation rate.
The method according to any one of claims 1-21, wherein the shaper parameters include at least one of a credit accumulation rate and a credit consumption rate.
A first device, characterized in that the first device includes:

an acquisition unit, configured to acquire traffic collection information of the data stream;

A processing unit, configured to determine shaper parameters according to the traffic collection information and SLA information corresponding to the data flow; the shaper parameters are used by the shaper to adjust the data flow to meet the SLA information indication transmission requirements.
The first device according to claim 24, wherein the processing unit is specifically configured to:

Obtaining a target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow; the target bandwidth is a minimum value of an available bandwidth that meets the transmission requirements indicated by the SLA information and is used to transmit the data flow;

The shaper parameters are determined based on the target bandwidth.
The first device according to claim 25, wherein, when the processing unit obtains the target bandwidth according to the traffic collection information and the SLA information corresponding to the data flow, the processing unit is specifically configured to:

Obtaining the range of the target bandwidth according to the traffic collection information;

The target bandwidth is obtained according to the range of the target bandwidth and the SLA information corresponding to the data flow.
The first device according to claim 26, wherein, within the range where the processing unit obtains the target bandwidth according to the traffic collection information, the processing unit is specifically configured to:

Determine the range of the target bandwidth according to a reference value and a correction value; the reference value is a reference value of the target bandwidth determined according to the flow collection information, and the correction value indicates that the target bandwidth is relative to the reference value of fluctuations.
The first device according to claim 26, wherein the range in which the processing unit obtains the target bandwidth according to the traffic collection information includes:

The first device determines the range of the target bandwidth according to a distribution fitting algorithm and the traffic collection information.
The first device according to claim 25, wherein the traffic collection information includes the length of the packets of the data flow in multiple collection periods; the processing unit according to the traffic collection information and the In the SLA information corresponding to the data flow obtained in the target bandwidth, the processing unit is specifically used for:

Acquiring the burst amount of the data flow according to the traffic collection information; the burst amount is the length of the message corresponding to each collection cycle in the plurality of collection cycles;

The target bandwidth is obtained by calculating according to the burst amount and the SLA information corresponding to the data flow.
The first device according to any one of claims 24-29, wherein the first device further comprises:

The first adjustment unit is configured to adjust the SLA information in response to the congestion degree being greater than a threshold, so that the data flow is adjusted according to the adjusted SLA information and the shaper parameters determined by the traffic collection information, so as to meet the requirements. The transmission requirement indicated by the SLA information and the congestion degree is less than or equal to the threshold;

and / or,

adjusting the queue into which the data flow enters, so as to meet the transmission requirement indicated by the SLA information and the congestion degree is less than or equal to the threshold;

and / or,

adjusting the transmission path of the data flow, so that the transmission of the data flow through the transmission path meets the transmission requirements indicated by the SLA information and the congestion degree is less than or equal to the threshold;

Wherein, the congestion degree is determined according to the remaining capacity of the forwarding device, and the remaining capacity refers to the remaining forwarding capability of the forwarding device when the committed forwarding delay of the forwarding device is guaranteed, and the committed forwarding delay is the A preset time delay for data streams to wait for processing in the forwarding device.
The first device according to any one of claims 24-29, wherein the first device further comprises:

The second adjusting unit, in response to the time delay for transmitting the data flow from the source end to the destination end, or the estimated value of the time delay for transmitting the data flow from the source end end to the destination end does not meet the transmission requirement of the SLA information, Adjusting the SLA information, so that the data flow is adjusted according to the adjusted SLA information and the shaper parameters determined by the traffic collection information, so as to meet the transmission requirements indicated by the SLA information;

and / or,

Adjusting the queue into which the data flow enters, so as to meet the transmission requirements indicated by the SLA information;

and / or,

Adjusting the transmission path of the data flow, so that the transmission of the data flow through the transmission path meets the transmission requirement indicated by the SLA information.
The first device according to any one of claims 24-31, wherein the SLA information includes an upper bound of a target delay; the upper bound of the target delay indicates that the data flow is from the source end to the destination The upper bound of the end delay.
The first device according to claim 32, wherein the target delay comprises a shaping delay; the shaping delay indicates a delay during processing of the data flow in the shaper.
The first device according to claim 33, wherein the target delay further includes one or more of fixed delay and network forwarding delay; the fixed delay includes propagation delay, device processing One or more of delay and port delay; the propagation delay is the delay of the data stream propagating in the transmission medium; the device processing delay is the delay of the device processing the data stream; The port transmission delay is the delay of transmitting the data flow through the port; the network forwarding delay is the pre-delay of the data flow waiting to be processed in the forwarding device from the source end to the destination end set delay.
The first device according to claim 34, wherein the network forwarding delay indicates the sum of committed forwarding delays of multiple forwarding devices transmitting the data flow; the committed forwarding delay is the The preset time delay for the data flow to be processed in the forwarding device.
The first device according to claim 34, wherein the network forwarding delay is determined according to a preset forwarding bandwidth of a plurality of forwarding devices transmitting the data stream; the preset forwarding bandwidth is the The forwarding device forwards the preset bandwidth of the data flow.
The first device according to claim 33, wherein the target delay further includes one or more of a fixed delay and an actual forwarding delay;

The actual forwarding delay indicates the delay of the data flow waiting to be processed in the forwarding device from the source end to the destination end.
The first device according to any one of claims 24-31, wherein the SLA information includes a buffer upper bound; the buffer upper bound is the device that transmits the data stream, including a shaper Minimum cacheable value available.
The first device according to any one of claims 32-38, wherein the SLA information further includes a reliability probability, and the reliability probability is a transmission requirement indicated by the SLA information corresponding to the data flow. probability.
The first device according to any one of claims 24-39, wherein the acquiring unit is specifically configured to:

receiving the traffic collection information of the data stream sent by a second device; the second device is a device for transmitting the data stream.
The first device according to claim 40, wherein the flow collection information includes statistical values of packet lengths of the data flow in multiple collection periods; the statistical values include average values, and the The average value indicates the ratio of the lengths of collecting the plurality of packets in the data stream to the number of acquisition cycles for collecting the plurality of packets.
The first device according to claim 40 or 41, wherein the first device further comprises:

A sending unit, configured to send the shaper parameters to a third device; the third device is a device that includes a shaper and transmits the data stream.
The first device according to any one of claims 24-42, wherein the first device is a control device or a device for transmitting the data stream.
The first device according to claim 43, wherein the control device is a central network control CNC device.
The first device according to any one of claims 24-44, wherein the shaper parameters include at least one of token bucket depth and token generation rate.
The first device according to any one of claims 24-44, wherein the shaper parameters include at least one of a credit accumulation rate and a credit consumption rate.
A network system, characterized in that the network system includes a first device and a second device,

The second device is configured to collect traffic collection information of the data stream, and send the traffic collection information of the data stream to the first device; the second device is a device for transmitting the data stream;

The first device is configured to receive the traffic collection information of the data stream sent by the second device;

The first device is further configured to determine a shaper parameter according to the traffic collection information and the SLA information corresponding to the data flow; the shaper parameter is used by the shaper to adjust the data flow to meet the The transmission requirements indicated by the above SLA information.
The network system according to claim 47, wherein the network system further comprises a third device,

The first device is further configured to send the shaper parameter to the third device;

The third device is configured to receive the shaper parameters sent by the first device, and configure the shaper according to the shaper parameters; the third device transmits the data including the shaper streaming device.