WO2022213617A1 - 用于动态流量整形的方法和装置 - Google Patents

用于动态流量整形的方法和装置 Download PDF

Info

Publication number
WO2022213617A1
WO2022213617A1 PCT/CN2021/132675 CN2021132675W WO2022213617A1 WO 2022213617 A1 WO2022213617 A1 WO 2022213617A1 CN 2021132675 W CN2021132675 W CN 2021132675W WO 2022213617 A1 WO2022213617 A1 WO 2022213617A1
Authority
WO
WIPO (PCT)
Prior art keywords
queue
rate
data
credit value
traffic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/132675
Other languages
English (en)
French (fr)
Inventor
唐宏
龚霞
朱永庆
陈华南
伍佑明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Telecom Corp Ltd
Original Assignee
China Telecom Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Telecom Corp Ltd filed Critical China Telecom Corp Ltd
Publication of WO2022213617A1 publication Critical patent/WO2022213617A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/16—Arrangements for providing special services to substations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H04L47/62—Queue scheduling characterised by scheduling criteria
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H04L47/62—Queue scheduling characterised by scheduling criteria
    • H04L47/624—Altering the ordering of packets in an individual queue

Definitions

  • the present application is based on the CN application number 202110366268.7 and the filing date is April 6, 2021, and claims its priority.
  • the disclosure of the CN application is hereby incorporated into the present application as a whole.
  • the present disclosure generally relates to the technical field of Quality of Service (QoS) in data communication, and more particularly relates to a CBS (Credit Based Shaper, credit-based shaping) mechanism.
  • QoS Quality of Service
  • CBS Clear Based Shaper, credit-based shaping
  • the IEEE 802.1Qav standard proposes a CBS mechanism, a credit-based traffic shaping mechanism.
  • Traffic shaping refers to measures to actively adjust the output rate of traffic.
  • the CBS mechanism sets the credit value for the forwarding state of the high-priority queue, so that the data transmission of this queue can only be carried out when the credit value is greater than or equal to 0, which realizes the limitation of time-sensitive flow bursts and guarantees its scheduling priority.
  • the CBS mechanism is implemented on the basis of the stream reservation protocol (802.1Qav).
  • This protocol calls the stream that has undergone bandwidth reservation as SR (Stream Reservation) class data, mainly including class A (class A) data and B class data.
  • Class (class B) data two types.
  • Type-A data and Type-B data are two different types of bandwidth reserved data streams defined by Ethernet Audio Video Bridging (AVB), where Type-A data has a higher priority than Type-B data. That is to say, when type A data and type B data meet the transmission conditions at the same time, type A data is preferentially forwarded.
  • the reserved bandwidth for various types of data is fixed, which leads to the following problems: if the reserved bandwidth for type A data or type B data is small, when the When the service rate is higher than the reserved bandwidth, there will be a large delay, and it is difficult to ensure the low delay requirement; if the reserved bandwidth of the A-type data or the B-type data is large, there will be a problem of wasting bandwidth.
  • the present disclosure proposes a credit value-based dynamic traffic shaping method that dynamically adjusts the reserved bandwidth based on the service rate.
  • the increase and decrease rates of the queue credit value are dynamically adjusted, thereby realizing the traffic shaping mechanism based on the real service transmission rate.
  • the method of the present disclosure can improve the transmission rate of common data flow, for example, best effort (Best Effort, BE) data, and reduce network delay while ensuring the low delay of high-priority service transmission.
  • a method for dynamic traffic shaping comprising: receiving a data frame transmitted at a service rate; making the data frame wait for transmission in a queue corresponding to its class, and calculating the data The credit value of the queue in which the frame is located, wherein the credit value increases at an increasing rate during the waiting period of the queue for transmission, and the increasing rate changes dynamically based on the traffic rate of the data frame in the queue; and the level in the queue with a credit value ⁇ 0 The highest data frame in the queue.
  • an apparatus for dynamic traffic shaping comprising: a memory having instructions stored thereon; and a processor configured to execute the instructions stored on the memory to perform an The method for dynamic traffic shaping described in the above aspects of the present disclosure.
  • a computer program product comprising computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform a The method for dynamic traffic shaping described in the above aspects of the present disclosure.
  • Figure 1 shows the traffic transmission model of the CBS mechanism
  • FIG. 2 shows a flowchart of a method for dynamic traffic shaping according to some embodiments of the present disclosure
  • FIG. 3 shows a flowchart of a method for dynamic traffic shaping according to other embodiments of the present disclosure
  • FIG. 4 shows a flowchart of a method for dynamic traffic shaping according to further embodiments of the present disclosure.
  • FIG. 5 shows an exemplary hardware configuration diagram of an apparatus for dynamic traffic shaping according to some embodiments of the present disclosure.
  • the present disclosure proposes a credit value-based dynamic traffic shaping method and device for dynamically adjusting reserved bandwidth based on a service rate.
  • the current CBS mechanism is mainly used in business scenarios with low latency and deterministic latency requirements.
  • the rate of increase and decrease of the queue credit value is based on the reserved bandwidth of the corresponding queue, and the reserved bandwidth is predetermined based on the traffic of various types of data. change automatically.
  • This static planning method will lead to waste of bandwidth or increase of delay when the service rate changes suddenly, and it is difficult to ensure low delay and deterministic delay requirements.
  • the method and device of the present disclosure realize the dynamic traffic shaping mechanism based on the real service transmission rate by dynamically adjusting the reserved bandwidth based on the real service rate, and then dynamically adjusting the increase and decrease rates of the queue credit value.
  • the method and device of the present disclosure improve the transmission rate of common data streams (eg, BE data), reduce network delay, and improve bandwidth utilization while ensuring low latency of high-priority service transmission.
  • common data streams eg, BE data
  • the CBS mechanism typically works at the output port of a switch, router, or similar device in Ethernet. Through the IEEE 802.1Qav priority remapping mechanism, data frames with different priorities are stored in the corresponding traffic class queues. The CBS mechanism provides queue management and traffic shaping for the traffic class queues reserved by the flow.
  • each queue that uses CBS as its transmission selection mechanism maintains a bounded value, that is, the credit value credit.
  • Queue data can only be transmitted when credit ⁇ 0. Specifically, when the credit value of both type A data and type B data reaches zero or more, type A data is transmitted; when the credit value of type A data is lower than zero and the credit value of type B data is higher than zero, type B data is transmitted. Class data; and when the credit values of both Class A data and Class B data are lower than zero, data in the normal data stream queue, such as BE data, is transmitted.
  • Figure 1 shows the traffic transmission model of the CBS mechanism.
  • the CBS selection mechanism meets the following conditions:
  • the queue meets the transmission condition only when the queue's credit ⁇ 0.
  • Port transmission rate such as the output port transmission rate of a switch, in bit/s.
  • –idleSlope The increase rate of the credit value, less than or equal to portTransmitRate (port transmission rate), in bit/s.
  • –operIdleSlope reserved bandwidth of the queue, in bit/s.
  • –credit The current credit value of the corresponding traffic class queue, which determines whether the data frame in the corresponding queue can be selected for transmission.
  • the unit is bit.
  • –hiCredit The maximum value of the credit value, that is, the maximum value of the credit value that can be accumulated during the waiting period, in bits; after the maximum value is reached, if the data in the queue has not yet started to transmit, the credit value will continue to remain at this value maximum value.
  • –loCredit The minimum value of the credit value, that is, the minimum value to which the credit value can be reduced during transmission, in bits; since the transmission is in units of frames, if the currently transmitted frame has not been transmitted when the credit value is reduced to zero After the transmission is completed, the credit value continues to decrease until the transmission of the frame is completed, so the minimum value is below zero.
  • the credit value credit determines the queue transmission selection, and the key indicators affecting credit are defined as:
  • the increase rate of the credit value of a queue of a data type is equal to the reserved bandwidth preset for the data type.
  • the reserved bandwidth is manually set by the administrator and does not change automatically during data forwarding. Therefore, the queue's credit increase rate does not automatically change during data forwarding. Since the credit value decrease rate is the difference between the increase rate and the port transmission rate, the decrease rate does not automatically change during data forwarding.
  • the present disclosure proposes a credit value-based dynamic traffic shaping method that dynamically changes the reserved bandwidth based on the actual service rate.
  • the method realizes the dynamic adjustment of the queue transmission bandwidth and its credit value increase/decrease rate by dynamically changing the reserved bandwidth based on the actual service rate of the data traffic during data forwarding.
  • the method optimizes the CBS traffic shaping mechanism, and improves the interface bandwidth utilization rate without affecting the time-sensitive service delay.
  • Figure 2 illustrates a dynamic traffic shaping method according to some embodiments of the present disclosure. This embodiment will be described below with reference to FIG. 2 .
  • a data frame transmitted at a service rate is received.
  • the generated data frame is transmitted to the output port of the switch at the service rate, and waits to be forwarded there.
  • the traffic rate of the data frame is the transmission rate of the data traffic, which is different based on the traffic performed by the user (eg, watching a video). When a large amount of traffic is generated, the service rate suddenly increases.
  • step 202 the data frame is made to wait for transmission in the queue corresponding to its category, and the credit value of the queue where the data frame is located is calculated, wherein the credit value increases at an increasing rate during the waiting period of the queue for transmission, and the increasing rate of the credit value is based on the data frame
  • the traffic rate varies dynamically in a positive correlation.
  • Received data frames are stored in the queue corresponding to the data frame type.
  • A-type data, B-type data, and ordinary data are stored in different queues, respectively, and corresponding credit values are maintained for each queue.
  • the credit value increases at an increasing rate during the waiting period of the queue, and the increasing rate varies dynamically based on a positive correlation with the traffic rate of the data frames in the queue. That is, the increase rate of the credit value increases with the increase of the service rate, and decreases with the decrease of the service rate.
  • the rate at which a queue's credit value increases reflects the length of time that queue's data is waiting to be transmitted. Since the increase rate of the credit value increases with the increase of the service rate when the traffic bursts, the waiting time of the data frame in the queue is reduced, and the transmission efficiency is improved. When the traffic is low, the increase rate of the credit value is correspondingly reduced, thereby saving bandwidth and reducing unnecessary waste.
  • step 203 the data frames in the queue with the highest level among the queues with the credit value ⁇ 0 are sent.
  • each queue data frame is selected and sent according to the CBS mechanism.
  • the CBS mechanism only queues with a credit value ⁇ 0 meet the transmission conditions, so the data frames in the queue with the highest level in the queue with a credit value ⁇ 0 are sent.
  • the positive correlation between the increase rate of the credit value and the service rate of the data frame can be set by those skilled in the art according to specific needs.
  • the rate of increase of the credit value of the queue may be proportional to the traffic rate of the data frames in the queue. In other embodiments, the rate of increase of the credit value of the queue is equal to the traffic rate of the data frames in the queue.
  • the credit value of the queue is equal to the reserved bandwidth of the queue data. Since the queue credit value changes dynamically based on the traffic rate of the data frames in the queue, the reserved bandwidth of the queue data also changes dynamically. It realizes the dynamic adjustment of queue transmission bandwidth and its credit value increase/decrease rate, optimizes the CBS traffic shaping mechanism, and improves the interface bandwidth utilization rate without affecting the time-sensitive service delay.
  • the decrease rate of the credit value is the difference between the increase rate of the credit value and the port transmission rate.
  • the increasing rate of the credit value increases, so the decreasing rate of the credit value decreases accordingly.
  • the service rate changes dynamically the increase or decrease rate of the credit value is dynamically adjusted to achieve traffic transmission within a more suitable queue transmission time, which reduces the impact of forwarding delay when the high-priority queue traffic rate is too large It can also release more resources for low-priority traffic transmission when its traffic rate is small.
  • the maximum transmission delay of type A data and type B data can be expressed as:
  • Delay A is the maximum transmission delay of type A data
  • Delay B is the maximum transmission delay of type B data
  • D TSB is the traffic shaping delay, that is, the delay for the credit value to increase from the lowest value loCredit to 0;
  • D LPB is the low-priority traffic blocking delay
  • D HPB is the high-priority traffic blocking delay; when there is high-priority queue data transmission, it is necessary to wait for the high-priority queue data to be transmitted or its credit value to decrease to the minimum value;
  • D TRANS is the transmission delay, that is, the transmission time of the data in the queue, which depends on the reduction rate sendSlope of the credit value; the queue obtains transmission opportunities by accumulating the credit value, and consumes the credit value during the transmission process.
  • FIG. 3 shows a flowchart of a dynamic traffic shaping method according to some embodiments of the present disclosure.
  • the rate of increase and decrease of the credit value can be updated in real time according to changes in the traffic rate.
  • step 301 CBS transmission selection is started.
  • idleSlope A can be set as the current service rate of type A data
  • idleSlope B can be set as the current service rate of type B data. If no traffic is currently generated, it can be set to the rate of the last received data stream. Then, based on the set idleSlope and the port transmission rate, the sendSlopes of the A-type data and the B-type data are calculated according to formula (2).
  • step 303 it is judged whether the current credit value of the A-type data queue is greater than or equal to 0 and the A-type data queue is not empty (ie, there are data frames waiting to be sent in the queue). If the condition is met, the flow proceeds to step 304 .
  • one data frame in the class A data queue is transmitted.
  • the credit value of the class A data queue decreases at the decreasing rate sendSlope A set in step 302
  • the credit value of the class B data queue increases at the increasing rate idleSlope B set in step 302 .
  • step 302 parameters idleSlope A , sendSlope A , idleSlope B and idleSlope B are updated according to the current service rates of various types of data streams.
  • the increase rate and decrease rate of the credit value of the A-type data and B-type data queues can be changed in real time with the change of the service rate. In this way, various parameters of the credit value can be quickly adjusted when the traffic bursts, reducing delays.
  • step 303 If it is determined in step 303 that the condition for type A data transmission is not satisfied, that is, the current credit value of the type A data queue is less than 0 or the queue is empty, the flow proceeds to step 305 .
  • step 305 it is determined whether the current credit value of the B-type data queue is greater than or equal to 0 and the B-type data queue is not empty (ie, there are data frames waiting to be sent in the queue). If the condition is met, the flow proceeds to step 306 .
  • a data frame in the class B data queue is transmitted.
  • the credit value of the class B data queue decreases at the decreasing rate sendSlope B set or updated at step 302
  • the credit value of the class A data queue increases at the increasing rate idleSlope A set or updated at step 302 .
  • the flow also returns to step 302 where the parameters are updated.
  • step 305 it is judged that the current credit value of the B-type data queue is less than 0 and the B-type data queue is empty, that is to say neither the A-type data transmission conditions nor the B-type data transmission conditions are satisfied, then the flow proceeds to step 307.
  • the BE queue is polled according to the priority and one data frame is transmitted therein. While the BE data is being transmitted, the credit values of the A-type data queue and the B-type data queue are respectively increased according to the increase rates idleSlope A and idleSlope B set or updated in step 302 . After the data frame is transmitted, the flow returns to step 302, and the parameters are updated.
  • the above embodiments realize that during the forwarding of data traffic, the increase rate and decrease rate of the credit value of the class A data and class B data queues change in real time with the change of the service rate. Therefore, various parameters of the credit value can be adjusted in real time to reduce delays. However, this is not required, and it can also be judged according to the actual situation whether it is necessary to adjust the increase rate and decrease rate of the credit value of the A-type data and B-type data queues.
  • FIG. 4 shows a flowchart of a dynamic traffic shaping method according to other embodiments of the present disclosure. Unlike the embodiments shown in FIG. 3 , in these embodiments, the credit value is not updated in real time based on the traffic rate, but is updated only when the traffic changes suddenly.
  • Steps 402-407 in the flow shown in FIG. 4 are similar to 302-307 in FIG. 3, and will not be described in detail here.
  • the difference between the embodiment shown in FIG. 4 and FIG. 3 is that, after each frame is transmitted, it does not directly return to step 402 to update the parameters of the increase rate and decrease rate, but proceeds to step 408 .
  • step 408 the difference between the credit value increase rate of the A-type data and the B-type data and the currently received service rate of the A-type data and the B-type data is calculated respectively. If the difference is greater than the predetermined threshold, return to step 402 to update the increase rate and decrease rate of the credit value of the A-type data and the B-type data. And proceed to step 403 after updating.
  • the credit value increase rates of the A-type data and the B-type data are not necessarily updated at the same time, but only one of the credit value increase rates of the A-type data and the B-type data may be updated.
  • Thresholds can be set as needed based on actual traffic. For example, it can be set to 20% of the traffic rate. Different thresholds can be set for Type A data and Type B data, or the same threshold can be used.
  • this embodiment Before updating the increase rate and decrease rate of the credit value, it is first determined whether the change of the service rate of the data is large enough, and the update is performed only when the change is large enough. Compared with the real-time update embodiment, this embodiment can save computing resources, and at the same time can ensure that the credit value increase rate and decrease rate can be dynamically adjusted even when the service rate changes greatly, so as to ensure the efficiency of data transmission.
  • FIG. 5 shows an exemplary configuration in which an apparatus 500 for dynamic traffic shaping according to an embodiment of the present disclosure may be implemented.
  • the dynamic traffic shaping apparatus 500 is an example of a hardware device to which the above-described aspects of the present disclosure can be applied.
  • Dynamic traffic shaping device 500 may be any machine configured to perform processing and/or computation.
  • Dynamic traffic shaping device 500 may be, but is not limited to, a switch, router, workstation, server, desktop computer, laptop computer, tablet computer, personal data assistant (PDA), smartphone, vehicle computer, or a combination thereof.
  • PDA personal data assistant
  • dynamic traffic shaping apparatus 500 may include one or more elements that may connect or communicate with bus 502 via one or more interfaces.
  • the bus 502 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, etc.
  • Dynamic traffic shaping apparatus 500 may include, for example, one or more processors 504 , one or more input devices 506 , and one or more output devices 508 .
  • the one or more processors 504 may be any kind of processors, and may include, but are not limited to, one or more general-purpose processors or special-purpose processors (such as special-purpose processing chips).
  • the processor 502 is, for example, configured to implement the dynamic traffic shaping method of the present disclosure.
  • Input device 506 may be any type of input device capable of inputting information to a computing device, and may include, but is not limited to, a mouse, keyboard, touch screen, microphone, and/or remote controller.
  • Output device 508 may be any type of device capable of presenting information, and may include, but is not limited to, displays, speakers, video/audio output terminals, vibrators, and/or printers.
  • the dynamic traffic shaping apparatus 500 may also include or be connected to a non-transitory storage device 514, which may be any storage device that is non-transitory and may implement data storage, and may include, but is not limited to, disk drives , optical storage device, solid state memory, floppy disk, flexible disk, hard disk, magnetic tape or any other magnetic medium, compact disk or any other optical medium, cache memory and/or any other memory chip or module, and/or from which a computer can read Any other medium from which data, instructions and/or code are fetched.
  • Dynamic traffic shaping device 500 may also include random access memory (RAM) 510 and read only memory (ROM) 512 .
  • RAM random access memory
  • ROM read only memory
  • ROM 512 may store programs, utilities or processes to be executed in a non-volatile manner.
  • RAM 510 may provide volatile data storage and store instructions related to the operation of dynamic traffic shaping device 500 .
  • Dynamic traffic shaping device 500 may also include a network/bus interface 516 coupled to data link 518 .
  • the network/bus interface 516 may be any kind of device or system capable of enabling communication with external devices and/or networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication devices, and/or chipsets (such as Bluetooth TM devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication facilities, etc.).
  • the present disclosure may be implemented as any combination of apparatus, system, integrated circuit, and computer program on a non-transitory computer-readable medium.
  • One or more processors may be implemented as integrated circuits (ICs), application specific integrated circuits (ASICs) or large scale integrated circuits (LSIs), system LSIs, super LSIs or ultra LSIs that perform some or all of the functions described in this disclosure components.
  • the present disclosure includes the use of software, applications, computer programs or algorithms.
  • Software, applications, computer programs or algorithms may be stored on a non-transitory computer readable medium to cause a computer, such as one or more processors, to perform the steps described above and described in the figures.
  • a computer such as one or more processors
  • one or more memories store software or algorithms in executable instructions
  • one or more processors may be associated with a set of instructions that execute the software or algorithms to provide various functions in accordance with the embodiments described in this disclosure.
  • Software and computer programs include machine instructions for programmable processors and can be written in high-level procedural languages, object-oriented programming languages, functional programming languages , logic programming language or assembly language or machine language.
  • computer-readable medium refers to any computer program product, apparatus, or device for providing machine instructions or data to a programmable data processor, such as magnetic disks, optical disks, solid-state storage devices, memories, and programmable logic devices (PLDs) , including a computer-readable medium receiving machine instructions as computer-readable signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本公开的一个方面涉及一种用于动态流量整形的方法，其中，所述方法包括：接收以业务速率传输的数据帧；使数据帧在与其类别对应的队列中等待传输，并计算数据帧所在队列的信用值，其中信用值在队列的等待传输期间以增加速率增加，并且增加速率基于所述队列中数据帧的业务速率正相关地动态变化；以及发送信用值≥0的队列中级别最高的队列中的数据帧。

Description

用于动态流量整形的方法和装置
相关申请的交叉引用
本申请是以CN申请号为202110366268.7，申请日为2021年4月6日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开总体上涉及数据通信中的服务质量(QoS)技术领域，并且更具体地涉及CBS(Credit Based Shaper，基于信用的整形)机制。
背景技术
IEEE 802.1Qav标准提出了CBS机制，即基于信用的流量整形机制。流量整形是指主动调整流量输出速率的措施。CBS机制通过为高优先级队列的转发状态设置信用值，使得只有信用值≥0时才能进行此队列的数据传输，实现了在限制时间敏感流突发的同时保证其调度的优先级。
CBS机制是在流预留协议(802.1Qav)基础上实现的，此协议将经过带宽预留的流称为SR(Stream Reservation)类(class)数据，主要包括A类(class A)数据和B类(class B)数据两类。A类数据和B类数据是以太网音视频桥接技术(AVB)定义的两种不同类型的带宽预留数据流，其中A类数据的优先级高于B类数据。也就是说，当A类数据和B类数据同时满足传输条件时，优先转发A类数据。
然而，在目前的CBS机制中，各类数据的预留带宽是固定的，从而导致以下问题：如果A类数据或B类数据的预留带宽较小，那么当A类数据或B类数据的业务速率高于其预留带宽时，将存在较大时延，难以保证低时延需求；如果A类数据或B类数据的预留带宽较大，则存在带宽浪费问题。
发明内容
在下文中给出了关于本公开的简要概述，以便提供关于本公开的一些方面的基本理解。但是，应当理解，这个概述并不是关于本公开的穷举性概述。它并不是意图用来确定本公开的关键性部分或重要部分，也不是意图用来限定本公开的范围。其目的仅仅是以简化的形式给出关于本公开的某些概念，以此作为稍后给出的更详细描述的 前序。
为了克服上述相关技术的弊端，本公开提出一种基于业务速率动态调整预留带宽的基于信用值的动态流量整形方法。通过基于真实业务速率动态调整预留带宽，来动态调整队列信用值的增加和减少速率，进而实现基于真实业务传输速率的流量整形机制。通过本公开的方法，能够在保障高优先级业务传输的低时延的同时，提高普通数据流，例如，尽力而为(Best Effort，BE)数据的传输速率，降低网络时延。
根据本公开的一个方面，提供一种用于动态流量整形的方法，其中，所述方法包括：接收以业务速率传输的数据帧；使数据帧在与其类别对应的队列中等待传输，并计算数据帧所在队列的信用值，其中信用值在队列的等待传输期间以增加速率增加，并且增加速率基于所述队列中数据帧的业务速率正相关地动态变化；以及发送信用值≥0的队列中级别最高的队列中的数据帧。
根据本公开的另一个方面，提供一种用于动态流量整形的装置，其包括：存储器，其上存储有指令；以及处理器，被配置为执行存储在所述存储器上的指令，以执行根据本公开的上述方面所述的用于动态流量整形的方法。
根据本公开的又一个方面，提供一种计算机程序产品，其包括计算机可执行指令，所述计算机可执行指令在由一个或多个处理器执行时，使得所述一个或多个处理器执行根据本公开的上述方面所述的用于动态流量整形的方法。
附图说明
构成说明书的一部分的附图描述了本公开的实施例，并且连同说明书一起用于解释本公开的原理。
参照附图，根据下面的详细描述，可以更清楚地理解本公开，其中：
图1示出了CBS机制的流量传输模型；
图2示出了根据本公开的一些实施例的用于动态流量整形的方法的流程图；
图3示出了根据本公开的另一些实施例的用于动态流量整形的方法的流程图；
图4示出了根据本公开的另一些实施例的用于动态流量整形的方法的流程图；以及
图5示出了根据本公开的一些实施例的用于动态流量整形的装置的示例性硬件配置图。
具体实施方式
参考附图进行以下详细描述，并且提供以下详细描述以帮助全面理解本公开的各种示例实施例。以下描述包括各种细节以帮助理解，但是这些细节仅被认为是示例，而不是为了限制本公开，本公开是由随附权利要求及其等同内容限定的。在以下描述中使用的词语和短语仅用于能够清楚一致地理解本公开。另外，为了清楚和简洁起见，可能省略了对公知的结构、功能和配置的描述。本领域普通技术人员将认识到，在不脱离本公开的精神和范围的情况下，可以对本文描述的示例进行各种改变和修改。
本公开提出了一种基于业务速率动态调整预留带宽的基于信用值的动态流量整形方法和装置。目前的CBS机制主要应用于低时延和确定性时延需求业务场景。在目前的CBS机制中，队列信用值的增加和减少速率基于相应队列的预留带宽，而预留带宽是基于各类数据的流量预先确定的，由管理员人工设置，在数据转发期间不会自动改变。这种静态规划的方式在业务速率突发变化时将导致带宽浪费或时延增大问题，难以保障低时延和确定性时延需求。
本公开的方法和装置通过基于真实业务速率来动态调整预留带宽，进而动态调整队列信用值的增加和减少速率，实现了基于真实业务传输速率的动态流量整形机制。本公开的方法和装置在保障高优先级业务传输的低时延的同时，也提高了普通数据流(例如，BE数据)的传输速率，降低了网络时延，提高了带宽利用率。
下面，描述CBS机制的基本原理。
CBS机制通常工作在以太网中的交换机、路由器或类似装置的输出端口处。通过IEEE 802.1Qav优先级重映射机制，将不同优先级的数据帧存入对应的流量类别(traffic class)队列，CBS机制为经过流预留的流量类别队列提供队列管理和流量整形。
CBS的基本原理为：每一个采用CBS作为其传输选择机制的队列，都维持一个有界的数值，即信用值credit。当credit≥0时，才可传输队列数据。具体而言，当A类数据和B类数据的信用值都达到零以上时，传输A类数据；当A类数据的信用值低于零而B类数据的信用值高于零时，传输B类数据；并且当A类数据和B类数据的信用值都低于零时，传输普通数据流队列中的数据，例如BE数据。
图1示出了CBS机制的流量传输模型。
CBS选择机制满足以下条件：
①当队列中有数据帧处于等待传输状态时，该队列对应的信用值以增加速率 idleSlope增加；
②当队列中的数据帧正在进行传输时，该队列对应的信用值以减小速率sendSlope减小；
③当前队列为空且对应的信用值大于0时，将信用值直接清0。
只有当队列的credit≥0时，队列才满足传输条件。
CBS机制的相关参数介绍如下：
–portTransmitRate：端口传输速率，例如交换机的输出端口传输速率，单位为bit/s。
–idleSlope：信用值的增加速率，小于等于portTransmitRate(端口传输速率)，单位为bit/s。
–operIdleSlope：队列的预留带宽，单位为bit/s。
–credit：相应流量类别队列当前的信用值，决定相应队列中的数据帧是否可以被选择传输，单位为bit。
–sendSlope：信用值的减小速率，单位为bit/s。
–maxFrameSize：最大帧长度，与流量类别相关，单位为bit。
–hiCredit：信用值的最大值，即在等待传输期间，信用值可积累达到的最大值，单位为bit；在达到最大值之后，如果队列中的数据尚未开始传输，则信用值继续保持在该最大值。
–loCredit：信用值的最小值，即在传输期间，信用值可减小达到的最小值，单位为bit；由于传输以帧为单位，如果在信用值减小到零时当前传输的帧还未完成传输，则信用值继续减小，直到该帧传输完毕，因此该最小值低于零。
–maxInterferenceSize：网络中干扰帧的最大长度，单位为bit。
其中，信用值credit决定了队列传输选择，影响credit的关键指标定义为：
–idleSlope＝operIdleSlope                      (1)
–sendSlope＝idleSlope–portTransmitRate        (2)
–hiCredit＝maxInterferenceSize*(idleSlope/portTransmitRate)   (3)
–loCredit＝maxFrameSize*(sendSlope/portTransmitRate)   (4)。
可见，一个数据类别的队列的信用值增加速率等于为该数据类别预先设置的预留带宽。如上文所述，预留带宽由管理员人工设置，在数据转发期间不会自动改变。因此，队列的信用值增加速率在数据转发期间不会自动改变。由于信用值减小速率为增 加速率和端口传输速率的差值，因此减小速率在数据转发期间也不会自动改变。
基于上述CBS基本原理，本公开提出一种基于实际业务速率动态改变预留带宽的基于信用值的动态流量整形方法。该方法通过在数据转发期间，基于数据流量的实际业务速率动态改变预留带宽，来实现队列传输带宽与其信用值增长/减小速率的动态调整。该方法优化了CBS流量整形机制，在不影响时间敏感业务时延的同时，提高接口带宽利用率。
图2示出了根据本公开的一些实施例的动态流量整形方法。下面参照图2对该实施例进行说明。
如图2所示，在步骤201，接收以业务速率传输的数据帧。以交换机为例，产生的数据帧以业务速率被传输到交换机输出端口，并在此等待转发。数据帧的业务速率是数据流量的传输速率，基于用户进行的业务(例如，观看视频)而不同。当大量流量产生时，业务速率突发增大。
在步骤202，使数据帧在与其类别对应的队列中等待传输，并计算数据帧所在队列的信用值，其中信用值在队列的等待传输期间以增加速率增加，并且信用值的增加速率基于数据帧的业务速率正相关地动态变化。
接收到的数据帧被存入与数据帧类型相对应的队列。例如，A类数据、B类数据和普通数据被分别存入不同的队列，并且分别为每个队列保持相应的信用值。信用值在队列的等待传输期间以增加速率增加，并且增加速率基于所述队列中数据帧的业务速率正相关地动态变化。也就是说，信用值的增加速率随业务速率的增加而增加，随业务速率的减小而减小。
队列信用值的增加速率反映该队列的数据等待传输的时长。由于在流量突发时，信用值的增加速率随业务速率的增加而增加，因此数据帧在队列中的等待时间减少，传输效率提高。而在流量低时，信用值的增加速率相应减小，从而可以节约带宽，减小不必要的浪费。
在步骤203，发送信用值≥0的队列中级别最高的队列中的数据帧。在该步骤中，按照CBS机制对各队列数据帧选择发送。根据CBS机制，只有信用值≥0的队列满足传输条件，因此发送信用值≥0的队列中级别最高的队列中的数据帧。
信用值的增加速率与数据帧的业务速率之间的正相关关系可以由本领域技术人员根据具体需要来设置。在一些实施例中，队列的信用值的增加速率可以与所述队列中数据帧的业务速率成正比关系。在另一些实施例中，队列的信用值的增加速率等于 所述队列中数据帧的业务速率。
如以上公式(1)所示，队列的信用值等于该队列数据的预留带宽。由于队列信用值基于所述队列中数据帧的业务速率正相关地动态变化，因此该队列数据的预留带宽也是动态变化的。实现了队列传输带宽与其信用值增长/减小速率的动态调整，优化CBS流量整形机制，在不影响时间敏感业务时延的同时，提高了接口带宽利用率。
如以上公式(2)所示，信用值的减小速率为信用值的增加速率与端口传输速率之差。当业务速率增加时，信用值的增加速率增大，因此信用值的减小速率相应减小。当业务速率动态变化时，信用值的增大或减小速率均动态调整，以实现在更适合的队列传输时间内进行流量传输，减轻了当高优先级队列流量速率过大时影响转发时延的问题，同时也能在其流量速率较小时释放更多资源进行低优先级流量传输。
下面，计算当采用以上实施例中的动态流量整形方法时A类数据和B类数据的时延。A类数据和B类数据的最大传输时延可以分别表示为：
Figure PCTCN2021132675-appb-000001
Figure PCTCN2021132675-appb-000002
其中，各参数的含义如下：
Delay A为A类数据的最大传输时延；
Delay B为B类数据的最大传输时延；
D TSB为流量整形时延，即信用值从最低值loCredit增长到0需要等待的时延；
D LPB为低优先级流量阻塞时延；当低优先级队列中有帧正在传输时不可打断，要等待这一帧传输完，因此低优先级流量阻塞时延最大为传输一帧的时间；
D HPB为高优先级流量阻塞时延；当有高优先级队列数据传输时，需等待高优先级队列数据传输完或其信用值减小到最小值；
D TRANS为传输时延，即队列中的数据的传输时间，取决于信用值的减小速率sendSlope；队列通过累积信用值获得传输机会，并在传输过程中消耗信用值。
通过以上公式分析A类数据和B类数据的最大传输时延可知，当业务速率大时，idleSlope增大，从而流量整形时延减小，这意味着等待传输的时间减小了；sendSlope减小，从而传输时延增加，这意味着传输时间槽增加。可见，数据传输的效率提高， 并且高优先级业务的时延减小。
图3示出了根据本公开一些实施例的动态流量整形方法的流程图。在这些实施例中，信用值的增加速率和减小速率能够根据业务速率的变化实时更新。
首先，在步骤301，开始CBS传输选择。
接着，在步骤302，设置或更新参数idleSlope A、sendSlope A、idleSlope B和idleSlope B。例如，在CBS机制开始启用时可以将idleSlope A设为A类数据当前的业务速率，将idleSlope B设为B类数据当前的业务速率。如果目前没有流量产生，可以将其设置为上一次接收的数据流的速率。然后，基于设置的idleSlope和端口传输速率，根据公式(2)分别计算A类数据和B类数据各自的sendSlope。
在步骤303，判断A类数据队列当前的信用值是否大于等于0且A类数据队列不为空(即，队列中已有等待发送的数据帧)。如果满足该条件，流程前进至步骤304。
在步骤304，传输A类数据队列中的一个数据帧。在传输过程中，A类数据队列的信用值以在步骤302设置的减小速率sendSlope A减小，同时B类数据队列的信用值以在步骤302设置的增加速率idleSlope B增加。在传输完这一帧之后，流程返回步骤302。
在步骤302，根据当前各类数据流的业务速率来更新参数idleSlope A、sendSlope A、idleSlope B和idleSlope B。
由于每传输一帧就更新一次参数，实现了A类数据和B类数据队列的信用值增加速率和减小速率随业务速率的变化而实时地变化。这样在流量突发时可以迅速对信用值各项参数进行调整，减小延误。
如果在步骤303，判断不满足A类数据传输条件，即A类数据队列当前的信用值小于0或者队列为空，则流程前进至步骤305。
在步骤305，判断B类数据队列当前的信用值是否大于等于0且B类数据队列不为空(即，队列中已有等待发送的数据帧)。如果满足该条件，流程前进至步骤306。
在步骤306，传输B类数据队列中的一个数据帧。在传输过程中，B类数据队列的信用值以在步骤302设置或更新的减小速率sendSlope B减小，同时A类数据队列的信用值以在步骤302设置或更新的增加速率idleSlope A增加。在传输完这一帧之后，流程同样返回步骤302，并在步骤302中更新参数。
如果在步骤305，判断B类数据队列当前的信用值小于0且B类数据队列为空，也就是说既不满足A类数据传输条件，又不满足B类数据传输条件，则流程前进至步 骤307。
在步骤307，按照优先级来轮询BE队列并传输其中的一个数据帧。在传输BE数据的同时，A类数据队列和B类数据队列的信用值分别根据在步骤302中设置或更新的增加速率idleSlope A和idleSlope B增加。在传输完这个数据帧后，流程返回步骤302，并更新参数。
以上实施例实现了在数据流量的转发期间，A类数据和B类数据队列的信用值增加速率和减小速率随业务速率的变化而实时地变化。从而可以即时对信用值各项参数进行调整，减小延误。但这不是必须的，也可以根据实际情况来判断是否需要调整A类数据和B类数据队列的信用值增加速率和减小速率。
图4示出了根据本公开另一些实施例的动态流量整形方法的流程图。与图3所示的实施例不同，在这些实施例中，信用值并不是基于业务速率实时更新的，而是仅当流量突发变化时才进行更新。
图4所示的流程中的步骤402-407与图3中的302-307类似，此处不再详述。图4所示实施例与图3的区别在于，每传输完一帧之后，不是直接返回步骤402以更新增加速率和减小速率的参数，而是前进到步骤408。在步骤408，分别计算A类数据和B类数据的信用值增加速率与当前接收的A类数据和B类数据的业务速率之间的差。如果差大于预定阈值，则返回步骤402更新A类数据和B类数据的信用值增加速率和减小速率。并在更新后前进至步骤403。如果差小于等于预定阈值，则无需更新参数，而是直接返回步骤403。A类数据和B类数据的信用值增加速率不一定是同时更新的，而是可以仅更新A类数据和B类数据的信用值增加速率中的其中一者。
阈值可以基于实际流量根据需要设置。例如，可以设置成业务速率的20％。可以为A类数据和B类数据分别设置不同阈值，也可使用一样的阈值。
在更新信用值增加速率和减小速率之前，先判断数据的业务速率的变化是否足够大，仅当变化足够大时才更新。与实时更新的实施例相比，本实施例可以节约计算资源，同时又能确保在业务速率变化大的情况下仍然可以对信用值增加速率和减小速率进行动态调整，保证数据传输的效率。
图5示出了可以实现根据本公开的实施例的用于动态流量整形的装置500的示例性配置。
动态流量整形装置500是能够应用本公开的上述方面的硬件设备的实例。动态流量整形装置500可以是被配置为执行处理和/或计算的任何机器。动态流量整形装置 500可以是但不限制于交换机、路由器、工作站、服务器、台式计算机、膝上型计算机、平板计算机、个人数据助手(PDA)、智能电话、车载计算机或以上组合。
如图5所示，动态流量整形装置500可以包括可以经由一个或多个接口与总线502连接或通信的一个或多个元件。总线502可以包括但不限于，工业标准架构(Industry Standard Architecture，ISA)总线、微通道架构(Micro Channel Architecture，MCA)总线、增强ISA(EISA)总线、视频电子标准协会(VESA)局部总线、以及外设组件互连(PCI)总线等。动态流量整形装置500可以包括例如一个或多个处理器504、一个或多个输入设备506以及一个或多个输出设备508。一个或多个处理器504可以是任何种类的处理器，并且可以包括但不限于一个或多个通用处理器或专用处理器(诸如专用处理芯片)。处理器502例如被配置为实现本公开中的动态流量整形方法。输入设备506可以是能够向计算设备输入信息的任何类型的输入设备，并且可以包括但不限于鼠标、键盘、触摸屏、麦克风和/或远程控制器。输出设备508可以是能够呈现信息的任何类型的设备，并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。
动态流量整形装置500还可以包括或被连接至非暂态存储设备514，该非暂态存储设备514可以是任何非暂态的并且可以实现数据存储的存储设备，并且可以包括但不限于盘驱动器、光存储设备、固态存储器、软盘、柔性盘、硬盘、磁带或任何其他磁性介质、压缩盘或任何其他光学介质、缓存存储器和/或任何其他存储芯片或模块、和/或计算机可以从其中读取数据、指令和/或代码的其他任何介质。动态流量整形装置500还可以包括随机存取存储器(RAM)510和只读存储器(ROM)512。ROM 512可以以非易失性方式存储待执行的程序、实用程序或进程。RAM 510可提供易失性数据存储，并存储与动态流量整形装置500的操作相关的指令。动态流量整形装置500还可包括耦接至数据链路518的网络/总线接口516。网络/总线接口516可以是能够启用与外部装置和/或网络通信的任何种类的设备或系统，并且可以包括但不限于调制解调器、网络卡、红外线通信设备、无线通信设备和/或芯片集(诸如蓝牙 TM设备、802.11设备、WiFi设备、WiMax设备、蜂窝通信设施等)。
本公开可以被实现为装置、系统、集成电路和非瞬时性计算机可读介质上的计算机程序的任何组合。可以将一个或多个处理器实现为执行本公开中描述的部分或全部功能的集成电路(IC)、专用集成电路(ASIC)或大规模集成电路(LSI)、系统LSI，超级LSI或超LSI组件。
本公开包括软件、应用程序、计算机程序或算法的使用。可以将软件、应用程序、计算机程序或算法存储在非瞬时性计算机可读介质上，以使诸如一个或多个处理器的计算机执行上述步骤和附图中描述的步骤。例如，一个或多个存储器以可执行指令存储软件或算法，并且一个或多个处理器可以关联执行该软件或算法的一组指令，以根据本公开中描述的实施例提供各种功能。
软件和计算机程序(也可以称为程序、软件应用程序、应用程序、组件或代码)包括用于可编程处理器的机器指令，并且可以以高级过程性语言、面向对象编程语言、功能性编程语言、逻辑编程语言或汇编语言或机器语言来实现。术语“计算机可读介质”是指用于向可编程数据处理器提供机器指令或数据的任何计算机程序产品、装置或设备，例如磁盘、光盘、固态存储设备、存储器和可编程逻辑设备(PLD)，包括将机器指令作为计算机可读信号来接收的计算机可读介质。
提供本公开的主题作为用于执行本公开中描述的特征的装置、系统、方法和程序的示例。但是，除了上述特征之外，还可以预期其他特征或变型。可以预期的是，可以用可能代替任何上述实现的技术的任何新出现的技术来完成本公开的部件和功能的实现。
另外，以上描述提供了示例，而不限制权利要求中阐述的范围、适用性或配置。在不脱离本公开的精神和范围的情况下，可以对所讨论的元件的功能和布置进行改变。各种实施例可以适当地省略、替代或添加各种过程或部件。例如，关于某些实施例描述的特征可以在其他实施例中被结合。
类似地，虽然在附图中以特定次序描绘了操作，但是这不应该被理解为要求以所示的特定次序或者以顺序次序执行这样的操作，或者要求执行所有图示的操作以实现所希望的结果。在某些情况下，多任务处理和并行处理可以是有利的。

Claims (10)

  1. 一种用于动态流量整形的方法，其中，所述方法包括：
    接收以业务速率传输的数据帧；
    使数据帧在与其类别对应的队列中等待传输，并计算数据帧所在队列的信用值，其中信用值在队列的等待传输期间以增加速率增加，并且增加速率基于所述队列中数据帧的业务速率正相关地动态变化；以及
    发送信用值≥0的队列中级别最高的队列中的数据帧。
  2. 根据权利要求1所述的方法，其中，队列的信用值的增加速率与所述队列中数据帧的业务速率成比例地变化。
  3. 根据权利要求1所述的方法，其中，队列的信用值的增加速率等于所述队列中数据帧的业务速率。
  4. 根据权利要求1所述的方法，还包括：实时地将队列的信用值的增加速率更新为所述队列中的数据帧的业务速率。
  5. 根据权利要求1所述的方法，还包括：
    监测队列的信用值的增加速率与所述队列中数据帧的当前业务速率之差；以及
    当差大于阈值时，将所述队列的信用值的增加速率更新为队列中的数据帧的当前业务速率。
  6. 根据权利要求1所述的方法，其中，队列的流量整形时延随所述队列中数据帧的业务速率的增大而减小。
  7. 根据权利要求1所述的方法，其中，队列中数据的传输时间槽随业务速率的增大而增大。
  8. 根据权利要求1所述的方法，其中，队列的信用值在队列的传输期间以减小 速率减小，并且减小速率随业务速率的增大而降低。
  9. 一种用于动态流量整形的装置，其中，所述装置包括：
    存储器，其上存储有指令；以及
    处理器，被配置为执行存储在所述存储器上的指令，以执行以根据权利要求1至8中的任一项所述的方法。
  10. 一种计算机程序产品，包括计算机可执行指令，其中，所述计算机可执行指令在由一个或多个处理器执行时实现如权利要求1至8中的任一项所述的方法。
PCT/CN2021/132675 2021-04-06 2021-11-24 用于动态流量整形的方法和装置 Ceased WO2022213617A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110366268.7 2021-04-06
CN202110366268.7A CN115242647A (zh) 2021-04-06 2021-04-06 用于动态流量整形的方法和装置

Publications (1)

Publication Number Publication Date
WO2022213617A1 true WO2022213617A1 (zh) 2022-10-13

Family

ID=83544977

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132675 Ceased WO2022213617A1 (zh) 2021-04-06 2021-11-24 用于动态流量整形的方法和装置

Country Status (2)

Country Link
CN (1) CN115242647A (zh)
WO (1) WO2022213617A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115865815A (zh) * 2022-11-14 2023-03-28 北京物芯科技有限责任公司 报文转发方法、装置、交换机、电子设备及可读存储介质
CN120769370A (zh) * 2025-09-05 2025-10-10 天翼物联科技有限公司 一种基于离散时间的5g专网调度方法、系统及5g基站

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115865810B (zh) * 2023-02-22 2023-06-09 浙江中控研究院有限公司 一种时间敏感网络中信用值流量调度系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003005227A1 (en) * 2001-07-05 2003-01-16 Sandburst Corporation Method and apparatus for allocating link bandwidth
US20030223445A1 (en) * 2002-06-04 2003-12-04 Sandeep Lodha Packet-based traffic shaping
CN1581790A (zh) * 2003-08-15 2005-02-16 中兴通讯股份有限公司 一种支持多端口多业务的多级调度的方法
US20140036672A1 (en) * 2012-08-06 2014-02-06 Renesas Electronics Europe Limited Calculating credit for controlling data frame transmission
CN112019392A (zh) * 2020-11-02 2020-12-01 之江实验室 一种用于tsn网络的多特征流接入方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003005227A1 (en) * 2001-07-05 2003-01-16 Sandburst Corporation Method and apparatus for allocating link bandwidth
US20030223445A1 (en) * 2002-06-04 2003-12-04 Sandeep Lodha Packet-based traffic shaping
CN1581790A (zh) * 2003-08-15 2005-02-16 中兴通讯股份有限公司 一种支持多端口多业务的多级调度的方法
US20140036672A1 (en) * 2012-08-06 2014-02-06 Renesas Electronics Europe Limited Calculating credit for controlling data frame transmission
CN112019392A (zh) * 2020-11-02 2020-12-01 之江实验室 一种用于tsn网络的多特征流接入方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"IEEE Standard for Local and Metropolitan Area Networks - Virtual Bridged Local Area Networks Amendment 12: Forwarding and Queuing Enhancements for Time-Sensitive Streams;IEEE Std 802.1Qav-2009 (Amendment to IEEE Std 802.1Q-2005)", IEEE STANDARD, IEEE, PISCATAWAY, NJ USA, 5 January 2010 (2010-01-05), Piscataway, NJ USA , pages C1 - 72, XP017604265, ISBN: 978-0-7381-6143-3 *
QUALCOMM INCORPORATED: "FS_5GLAN: Time Sensitive Networking (TSN) Discussion Paper", 3GPP DRAFT; S1-174199 FS_5GLAN TIME SENSITIVE NETWORKING (TSN) DISCUSSION PAPER, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG1, no. Reno, USA; 20171127 - 20171201, 15 November 2017 (2017-11-15), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051378830 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115865815A (zh) * 2022-11-14 2023-03-28 北京物芯科技有限责任公司 报文转发方法、装置、交换机、电子设备及可读存储介质
CN120769370A (zh) * 2025-09-05 2025-10-10 天翼物联科技有限公司 一种基于离散时间的5g专网调度方法、系统及5g基站

Also Published As

Publication number Publication date
CN115242647A (zh) 2022-10-25

Similar Documents

Publication Publication Date Title
WO2022213617A1 (zh) 用于动态流量整形的方法和装置
US8218437B2 (en) Shared shaping of network traffic
US11258717B2 (en) Method for sending service packet, network device, and system
WO2020199792A1 (zh) 通信方法、装置、计算机可读介质及电子设备
US10382223B2 (en) Scheme for supporting wireless transmission taking into account QoS of USB application data
US20160142317A1 (en) Management of an over-subscribed shared buffer
WO2018113426A1 (zh) 一种流量控制方法及交换设备
CN114205302A (zh) 一种无损流量拥塞自适应方法、系统和网络设备
CN111131061B (zh) 一种数据传输方法及网络设备
US20130208593A1 (en) Method and apparatus providing flow control using on-off signals in high delay networks
CN100496022C (zh) 一种流量控制的方法及装置
EP2093945A1 (en) A method for realizing back pressure of masses of ports and the device thereof
CN107257962A (zh) 用于通用串行总线的协议适配层数据流控制
WO2021047404A1 (zh) 一种网络参数配置方法及装置
CN110830388B (zh) 一种数据调度方法、装置、网络设备及计算机存储介质
CN101478486B (zh) 一种交换网数据调度方法、设备和系统
US12328266B2 (en) Flow control method, apparatus, and device, and computer-readable storage medium
CN108632162B (zh) 一种队列调度方法及转发设备
WO2022174444A1 (zh) 一种数据流传输方法、装置及网络设备
CN114268987A (zh) 服务质量策略调整方法、装置及计算机可读介质
WO2016090607A1 (zh) 回传终端、基站及无线网络流量控制方法
CN119766743A (zh) 一种数据流传输方法、装置、设备及存储介质
CN109391558B (zh) 一种队列的控制方法及控制装置
CN113794585B (zh) 一种报文处理方法及装置
CN116016357A (zh) 数据传输的方法、装置、存储介质以及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21935834

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21935834

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21935834

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 25/03/2024)