WO2021098730A1 - 交换网络拥塞管理方法、装置、设备和存储介质 - Google Patents

交换网络拥塞管理方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2021098730A1
WO2021098730A1 PCT/CN2020/129822 CN2020129822W WO2021098730A1 WO 2021098730 A1 WO2021098730 A1 WO 2021098730A1 CN 2020129822 W CN2020129822 W CN 2020129822W WO 2021098730 A1 WO2021098730 A1 WO 2021098730A1
Authority
WO
WIPO (PCT)
Prior art keywords
token bucket
type
queue
congestion
bucket
Prior art date
Application number
PCT/CN2020/129822
Other languages
English (en)
French (fr)
Inventor
张瑛
刘衡祁
牛忠华
唐美芹
Original Assignee
深圳市中兴微电子技术有限公司
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 深圳市中兴微电子技术有限公司 filed Critical 深圳市中兴微电子技术有限公司
Publication of WO2021098730A1 publication Critical patent/WO2021098730A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/21—Flow control; Congestion control using leaky-bucket
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/215—Flow control; Congestion control using token-bucket
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/29—Flow control; Congestion control using a combination of thresholds
    • 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
    • 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
    • H04L47/622—Queue service order
    • 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
    • H04L47/6245—Modifications to standard FIFO or LIFO

Definitions

  • This application relates to the field of communications, for example, to a method, device, device, and storage medium for congestion management of a switching network.
  • the switching system is the main component of packet switching equipment.
  • Figure 1 is a structural diagram of a switching system under a single-level switching network. As shown in Figure 1, the switching system includes two business units (respectively business unit A and business unit C) and a switching unit B. The source switching access unit on the business unit A sends information elements through the switching unit B. Reach multiple destinations on service unit C to exchange access units.
  • Asymmetric switching network refers to the inconsistency of bandwidth between the source switching access unit to the switching unit, and the switching unit to the destination switching access unit, that is, the link bandwidth of the incoming switching unit and the outgoing switching unit are inconsistent.
  • Figure 2 is a structural diagram of a switching system under an asymmetric switching network. As shown in Figure 2, the link between the 0# switching access unit in the switching unit B and the service unit C fails, which results in the failure of the service unit A to the switching unit B, and the switching unit B to the service unit C Inconsistent bandwidth occurs.
  • 0# switching access unit, 1# switching access unit, 2# switching access unit in business unit A and 0# switching access unit, 1# switching access unit, 2 in business unit C #Switching access unit is a mutually symmetrical structure, but in the actual product application process, the link may fail. Once the link fails, the switching unit system will appear congested.
  • a bucket can be used to control the authorization distribution of all queues at the device level (that is, the place where the overall authorization is controlled). But with the improvement of product demand, authorization management control is not only the remote and local unicast authorization, but also the local multicast authorization. In the case of unicast congestion in the switching system, authorization is applied at the original port level, but a bucket is still used to control all unicast queue applications. In the case of congestion, the true port-level authorization ratio will be inaccurate. .
  • the present application provides a switching network congestion management method, device, equipment, and storage medium. Under the premise that the user configures the port-level weights correctly, the user needs are met and the service quality performance of the system is improved.
  • a switching network congestion management method including:
  • a congestion management device for a switching network including:
  • the obtaining module is set to obtain the congestion condition of the switching network; the first adjustment module is set to adjust the token amount of the first type token bucket according to the congestion condition; the second adjustment module is set to be set when the traffic request instruction is detected In this case, the amount of tokens of the second type token bucket corresponding to the queue where the traffic request instruction is located is adjusted.
  • a device including: a memory, and one or more processors; the memory is configured to store one or more programs; when the one or more programs are executed by the one or more processors, The one or more processors are enabled to implement the above-mentioned switching network congestion management method.
  • a storage medium is also provided, the storage medium stores a computer program, and when the computer program is executed by a processor, the foregoing switching network congestion management method is implemented.
  • Figure 1 is a structural diagram of a switching system under a single-stage switching network
  • Figure 2 is a structural diagram of a switching system under an asymmetric switching network
  • FIG. 3 is a flowchart of a switching network congestion management method provided by an embodiment of the present application.
  • Figure 4 is a schematic diagram of an application status to a superior
  • FIG. 5 is a schematic diagram of an application state to a higher level according to an embodiment of the present application.
  • Fig. 6 is a structural block diagram of a switching network congestion management device provided by an embodiment of the present application.
  • Fig. 7 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • Fig. 3 is a flowchart of a congestion management method for a switching network provided by an embodiment of the present application. This embodiment is applied to a situation where congestion occurs in a switching network such as a switch or a router. This embodiment may be executed by a device.
  • the device may be a switching access device.
  • the method in this embodiment includes S110-S130.
  • the switching network may be a single-stage switching network or a multi-stage switching network, which is not limited.
  • the switching system under the single-stage switching network as shown in FIG. 2 is taken as an example to describe the switching network congestion management method.
  • the switching system includes three source switching access units, three switching units and three destination switching access units. Between the 0# switching access unit in business unit C and the three switching units in switching unit B The link fails, which may cause the switch unit B to appear congested.
  • the current congestion condition of the switching network refers to the congestion condition of the link between multiple switching units and the switching access unit in the switching system, that is to say, other than the failed link in the switching system
  • the congestion of the link that is, 0# exchange unit is exchanged with 1# exchange access unit and 2# exchange access unit, 1# exchange unit is exchanged with 1# exchange access unit and 2# exchange access unit, 2# exchange
  • the unit exchanges access unit with 1# and exchange access unit with 2# respectively, and the congestion status of these six links.
  • S120 Adjust the amount of tokens in the token bucket of the first type according to the current congestion situation.
  • the token bucket refers to the internal storage pool of the network device, and the token refers to a virtual information packet that fills the token bucket at a given rate.
  • the first type token bucket refers to the total internal storage pool of the entire exchange system; the token amount refers to the total amount of virtual information packets that can be filled in the first type token bucket.
  • the token amount of the first type token bucket is smaller.
  • the amount of tokens in the first type token bucket is reduced.
  • the second type token bucket refers to the internal storage pool of each port-level corresponding token bucket. In an embodiment, the second type token bucket has a smaller internal storage pool than the first type token bucket.
  • the number of token buckets of the second type is related to the number of port-levels. The two are the same and correspond to each other one to one. Each second type token bucket controls a port level.
  • the flow request instruction refers to the message information sent by the user to the switching network through the port.
  • the traffic request command may be a request command for a fixed period of required traffic, for example, it may be a bandwidth of 20 megabits per second.
  • the first-type token bucket is used to control the number of all port-level second-type token buckets
  • the second-type token bucket is used to apply for authorization to the superior.
  • the second type of token bucket corresponding to the port level is implemented to apply for authorization to the upper level, thereby meeting user needs and improving the quality of service (QoS) performance of the switching system.
  • QoS quality of service
  • adjusting the amount of tokens in the token bucket of the first type according to the current congestion situation includes: calculating the corresponding total congestion value according to the congestion status of each channel in the exchange unit received in advance; according to the preset congestion The threshold value and the total congestion value determine the corresponding congestion level; determine the corresponding authorized issuance interval according to the congestion level; adjust the token amount of the first type token bucket according to the authorized issuance interval.
  • each channel refers to each link between each switching unit and the switching access unit.
  • the total congestion value is the sum of the corresponding congestion values of multiple channels in the switching network. After obtaining the corresponding total congestion value according to the congestion status of each channel, compare and analyze the total congestion value with the preset congestion threshold value configured in advance. If the total congestion value reaches the preset congestion threshold value, it is a congestion. grade. There are multiple preset congestion thresholds, and different preset congestion thresholds are thresholds of different congestion levels.
  • the preset congestion thresholds are a1, b1, and c1, respectively, when the total congestion value reaches a1, the corresponding congestion level is A level; when the total congestion value reaches b1, the corresponding congestion The level is B level; when the total congestion value reaches c1, the corresponding congestion level is C level.
  • a1>b1>c1 correspondingly, the congestion situation corresponding to different congestion levels, A>B>C, that is, the congestion situation corresponding to the A level is the most serious, and the congestion situation corresponding to the C level is the lightest; that is, the A level The corresponding level is the highest, and the C level is the lowest.
  • the authorization issuing interval of the queue in a case where the congestion level is high, in order to ensure the processing capability of the message, the authorization issuing interval of the queue can be increased accordingly to reduce the authorization distribution of the queue. That is, when the congestion level is A level, the corresponding authorization issuance interval is the largest; when the congestion level is C, the corresponding authorization issuance interval is the smallest. In other words, different congestion levels have different authorization issuance intervals.
  • the tokens of the first type of token bucket are increased or decreased according to the authorized issuance interval, that is, the order of adjusting the first type of token bucket The amount of cards.
  • the method when the flow request instruction is detected, before adjusting the token amount of the second type token bucket corresponding to the queue where the flow request instruction is located, the method further includes: determining the corresponding number according to the sequence number of the queue where the flow request instruction is located. The first threshold value, current bucket depth and weight coefficient of the second type token bucket; according to the comparison result of the current bucket depth of the second type token bucket and the first threshold value, determine the corresponding value of the second type token bucket Queue entry and exit status of First Input First Output (FIFO).
  • FIFO First Input First Output
  • the first threshold value corresponding to the second type token bucket can be selected according to the sequence number of the queue where the flow request instruction is located.
  • the first threshold refers to the lowest threshold of the second type of token bucket, that is, when the current bucket depth of the second type of token bucket is less than the lowest threshold, the second type of token bucket needs to enter the queuing FIFO Waiting to be served, that is, the queue that is authorized for distribution or the scanned queue is put into the second type token bucket.
  • adjusting the amount of tokens of the second type token bucket corresponding to the queue where the flow request instruction is located includes: adjusting the second type token when the queue where the flow request instruction is located is authorized for distribution or the queue is scanned. The amount of tokens in the bucket.
  • the authorization distribution of the queue corresponding to the second type token bucket is valid or the queue is scanned, it is necessary to apply for information to the superior through the second type token bucket where the queue is located, that is, in the second type token bucket
  • the bucket processes the queue, it performs a subtraction operation on the current bucket depth of the second type token bucket.
  • the switching network congestion management method when the queue FIFO is not empty and the sequence number of the queue is obtained, the switching network congestion management method further includes: determining the second threshold of the second type token bucket in which the queue is located according to the sequence number of the queue Value, current bucket depth and weight coefficient; adjust the token amount of the first type token bucket according to the weight coefficient.
  • the sequence number of the queue read from the queue FIFO is used to select the second threshold value of the token bucket of the second type. And read out the current bucket depth and weight coefficient of the second type token bucket, and adjust the amount of tokens required to be reduced by the first type token bucket according to the weight coefficient.
  • the weight coefficient of the token bucket of the second type is used to characterize the amount of tokens required to be reduced by the token bucket of the first type.
  • the amount of tokens required to be reduced by the token bucket of the first type may be equal to the weight coefficient of the token bucket of the second type, or may be in a certain proportion, which is not limited.
  • the token of the first type can be calculated The amount of tokens in the bucket.
  • adjusting the token amount of the second type token bucket corresponding to the queue where the traffic request instruction is located includes: adjusting the token amount of the second type token bucket corresponding to the queue according to the token amount of the first type token bucket The amount of cards.
  • the amount of tokens required to be increased by the second type of token bucket is the same as the amount of tokens required to be reduced by the first type of token bucket.
  • the amount of tokens required to be increased by the token bucket of the first type is taken as the amount of tokens required to be reduced by the token bucket of the second type.
  • the method further includes: determining the entry and exit status of the corresponding queuing FIFO according to the current bucket depth of the second type token bucket; Update the current bucket depth and report information of the second type token bucket.
  • the second threshold value refers to the highest threshold value of the token bucket of the second type.
  • the second type token bucket needs to be out of the queuing FIFO, that is, there is no need to add to the second type token bucket Authorized to distribute valid or scanned queues.
  • update the current bucket depth of the second type token bucket and the information requested by the superior to re-execute the operation of adjusting the token amount of the first type token bucket and the token amount of the second type token bucket.
  • Figure 4 is a schematic diagram of an application status to a superior. As shown in Figure 4, a bucket is used to control all unicast queue applications, which leads to inaccurate port-level authorization ratios under congestion conditions.
  • Fig. 5 is a schematic diagram of a state of applying to an upper level according to an embodiment of the present application.
  • a first-type token bucket is used to control the number of all port-level second-type token buckets, and the second-type token bucket is used to apply for authorization to the upper level, so that the user configures the correct port-level weights.
  • the needs of users are met and the QoS performance of the switching system is improved.
  • the process of applying for a status to the superior is described.
  • the bucket information of the current operation is obtained, and the normal threshold (ie, the normal) threshold of the corresponding bucket is selected through the corresponding queue sequence number.
  • the first threshold value read the bucket depth, weight coefficient and other information of the bucket corresponding to the queue to confirm whether the bucket needs to enter the queue FIFO and wait to be served.
  • the bucket depth of the bucket will be updated. .
  • the queue sequence number obtained after the queuing FIFO is not empty and is read out.
  • the queue sequence number is used to determine the off threshold (ie, the second threshold) of the bucket to select the corresponding bucket, and the latest bucket of the bucket is read at the same time.
  • the depth, weight coefficient and other information, according to the weight coefficient know the amount of tokens that the big bucket needs to reduce at this time, and it is also the amount of tokens that should be added to the small bucket at this time. Then, according to the current bucket depth of the small bucket, it is judged whether the small bucket still needs to enter the queuing FIFO or exit the queuing FIFO again. Then, update the bucket depth of the keg and the information requested by the superior.
  • the adding operation to the big bucket can be judged according to the current congestion situation of the switching network.
  • the congestion situation of the switching network is determined by calculating a total congestion value from the congestion status received by different channels in the switching unit, and then according to the pre-configured congestion threshold (ie, the preset congestion threshold). Congestion level, and configure different authorization issuance intervals for different congestion levels to adjust the amount of tokens in the first type of token bucket.
  • Fig. 6 is a structural block diagram of a switching network congestion management device provided by an embodiment of the present application. This embodiment is applied to a situation where congestion occurs in a switching network such as a switch or a router. As shown in FIG. 6, the device in this embodiment includes: an acquisition module 210, a first adjustment module 220, and a second adjustment module 230.
  • the obtaining module 210 is set to obtain the current congestion situation of the switching network; the first adjustment module 220 is set to adjust the token amount of the token bucket of the first type according to the current congestion situation; the second adjustment module 230 is set to When the flow request instruction is detected, the amount of tokens of the second type token bucket corresponding to the queue where the flow request instruction is located is adjusted.
  • the switching network congestion management device provided in this embodiment is configured to implement the switching network congestion management method of the embodiment shown in FIG. 3, and the implementation principles and effects of the switching network congestion management device provided in this embodiment are similar, and will not be repeated here.
  • the first adjustment module includes:
  • the calculating unit is set to calculate the corresponding total congestion value according to the congestion state of each channel in the switching unit received in advance; the first determining unit is set to determine the corresponding total congestion value according to the preset congestion threshold value and the total congestion value Congestion level; the second determining unit is configured to determine the corresponding authorization issuance interval according to the congestion level; the first adjustment unit is configured to adjust the token amount of the first type token bucket according to the authorization issuance interval.
  • the switching network congestion management device further includes:
  • the first determining module is configured to, when the flow request instruction is detected, before adjusting the token amount of the second type token bucket corresponding to the queue where the flow request instruction is located, according to the sequence number of the queue where the flow request instruction is located Determine the first threshold value, current bucket depth, and weight coefficient corresponding to the second type token bucket; the second determining module is set to be based on the current bucket depth of the second type token bucket and the first threshold value The result of the comparison is to determine the entry and exit status of the queuing FIFO corresponding to the second type token bucket.
  • the second adjustment module is configured to adjust the amount of tokens in the second type token bucket when the authorization distribution of the queue where the traffic request instruction is located is valid or the queue is scanned.
  • the switching network congestion management device further includes:
  • the third determining module is configured to determine the second threshold value and the current bucket of the second type token bucket in which the queue is located according to the sequence number of the queue when the queue is not empty and the sequence number of the queue is obtained. Depth and weight coefficient; the third adjustment module is configured to adjust the token amount of the token bucket of the first type according to the weight coefficient.
  • the second adjustment module is further configured to adjust the token amount of the second type token bucket corresponding to the queue according to the token amount of the first type token bucket.
  • the switching network congestion management device further includes:
  • the fourth determining module is configured to determine the corresponding queuing FIFO according to the current bucket depth of the second type token bucket after the adjustment of the token amount of the second type token bucket corresponding to the queue where the flow request instruction is located The entry and exit situation; the update module is configured to update the current bucket depth and report information of the second type token bucket.
  • Fig. 7 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • the device provided by the present application includes: a processor 310 and a memory 320.
  • the number of processors 310 in the device may be one or more. In FIG. 7, one processor 310 is taken as an example.
  • the number of memories 320 in the device may be one or more, and one memory 320 is taken as an example in FIG. 7.
  • the processor 310 and the memory 320 of the device are connected by a bus or in other ways. In FIG. 7, the connection by a bus is taken as an example.
  • the device is a switching access device.
  • the memory 320 can be configured to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the device of any embodiment of the present application (for example, the acquisition in the switching network congestion management apparatus).
  • the memory 320 may include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the device, and the like.
  • the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 320 may include a memory remotely provided with respect to the processor 310, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the above-provided device can be configured to execute the switching network congestion management method provided by any of the above-mentioned embodiments, and has corresponding functions and effects.
  • the embodiment of the present application also provides a storage medium containing computer-executable instructions.
  • the computer-executable instructions are executed by a computer processor, they are used to execute a switching network congestion management method.
  • the method includes: obtaining the current congestion status of the switching network Adjust the amount of tokens in the token bucket of the first type according to the current congestion situation; adjust the amount of tokens in the token bucket of the second type corresponding to the queue where the flow request instruction is located in the case of detecting a flow request instruction.
  • user equipment encompasses any suitable type of wireless user equipment, such as mobile phones, portable data processing devices, portable web browsers, or vehicular mobile stations.
  • the various embodiments of the present application can be implemented in hardware or dedicated circuits, software, logic or any combination thereof.
  • some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the present application is not limited thereto.
  • Computer program instructions can be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or written in any combination of one or more programming languages Source code or object code.
  • ISA Instruction Set Architecture
  • the block diagram of any logic flow in the drawings of the present application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions.
  • the computer program can be stored on the memory.
  • the memory can be of any type suitable for the local technical environment and can be implemented using any suitable data storage technology, such as but not limited to read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), optical Memory devices and systems (Digital Video Disc (DVD) or Compact Disk (CD)), etc.
  • Computer-readable media may include non-transitory storage media.
  • the data processor can be any type suitable for the local technical environment, such as but not limited to general-purpose computers, special-purpose computers, microprocessors, digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (ASICs) ), programmable logic devices (Field-Programmable Gate Array, FPGA), and processors based on multi-core processor architecture.
  • DSP Digital Signal Processing
  • ASICs application specific integrated circuits
  • FPGA Field-Programmable Gate Array
  • FPGA Field-Programmable Gate Array

Abstract

本文公开一种交换网络拥塞管理方法、装置、设备和存储介质。该交换网络拥塞管理方法包括：获取交换网的拥塞情况；根据拥塞情况调整第一类型令牌桶的令牌量；在检测到流量请求指令的情况下，通过第一类型令牌桶调整流量请求指令所在队列对应的第二类型令牌桶的令牌量。

Description

交换网络拥塞管理方法、装置、设备和存储介质
本申请要求在2019年11月20日提交中国专利局、申请号为201911143444.X的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域，例如涉及一种交换网络拥塞管理方法、装置、设备和存储介质。
背景技术
交换系统是分组交换设备的主要组成部分。图1是一种单级交换组网下的交换系统结构图。如图1所示，该交换系统包括两个业务单元(分别为业务单元A和业务单元C)和一个交换单元B，业务单元A上的源交换接入单元发出的信元，经过交换单元B到达业务单元C上的多个目的交换接入单元。
交换网络非对称是指在源交换接入单元到交换单元，和交换单元到目的交换接入单元之间，存在带宽不一致的情况，即进入交换单元和出交换单元的链路带宽不一致。图2是一种非对称交换组网下的交换系统结构图。如图2所示，交换单元B和业务单元C中的0#交换接入单元之间的链路出现失效现象，从而导致业务单元A到交换单元B，和交换单元B到业务单元C之间出现带宽不一致的情况。
在设计上，业务单元A中的0#交换接入单元、1#交换接入单元、2#交换接入单元与业务单元C中的0#交换接入单元、1#交换接入单元、2#交换接入单元是相互对称性结构，但实际产品应用过程中，链路存在失效可能性，一旦链路有失效，则交换单元系统中会出现拥塞状态。
为了避免交换系统中出现拥塞状态，可在器件级(即控制整体授权下发的地方)，采用一个桶控制所有队列的授权分发。但随着产品需求的提升，授权管理控制不仅仅是远端和本地的单播授权，还需要控制本地的多播授权。在交换系统中的单播出现拥塞的情况下，在原来的端口级申请授权，但仍然采用一个桶控制所有单播队列的申请，会在拥塞的情况下，导致真正的端口级授权比例不准确。
发明内容
本申请提供一种交换网络拥塞管理方法、装置、设备和存储介质，在用户 配置端口级权重正确的前提下，满足了用户需求，提高了系统的服务质量性能。
提供了一种交换网络拥塞管理方法，包括：
获取交换网的拥塞情况；根据所述拥塞情况调整第一类型令牌桶的令牌量；在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
还提供了一种交换网络拥塞管理装置，包括：
获取模块，设置为获取交换网的拥塞情况；第一调整模块，设置为根据所述拥塞情况调整第一类型令牌桶的令牌量；第二调整模块，设置为在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
还提供了一种设备，包括：存储器，以及，一个或多个处理器；存储器，设置为存储一个或多个程序；当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现上述的交换网络拥塞管理方法。
还提供了一种存储介质，所述存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述的交换网络拥塞管理方法。
附图说明
图1是一种单级交换组网下的交换系统结构图；
图2是一种非对称交换组网下的交换系统结构图；
图3是本申请实施例提供的一种交换网络拥塞管理方法的流程图；
图4是一种向上级申请状态的示意图；
图5是本申请实施例提供的一种向上级申请状态的示意图；
图6是本申请实施例提供的一种交换网络拥塞管理装置的结构框图；
图7是本申请实施例提供的一种设备的结构示意图。
具体实施方式
下文中将结合附图对本申请的实施例进行说明。
图3是本申请实施例提供的一种交换网络拥塞管理方法的流程图。本实施例应用于交换机或路由器等交换网络中出现拥塞的情况。本实施例可以由设备来执行，示例型地，设备可以为交换接入设备。
如图3所示，本实施例中的方法包括S110-S130。
S110、获取交换网的当前拥塞情况。
在实施例中，交换网可以为单级交换网络，也可以为多级交换网络，对此并不进行限定。在实施例中，以如图2所示的单级交换组网下的交换系统为例，对交换网络拥塞管理方法进行说明。在交换系统中包含三个源交换接入单元、三个交换单元和三个目的交换接入单元，在业务单元C中的0#交换接入单元与交换单元B中的三个交换单元之间的链路出现失效现象，导致交换单元B可能出现拥塞状态。
在实施例中，交换网的当前拥塞情况，指的是交换系统中多个交换单元与交换接入单元之间链路的拥塞情况，也就是说，交换系统中除失效链路之外的其它链路的拥塞情况，即0#交换单元分别与1#交换接入单元和2#交换接入单元，1#交换单元分别与1#交换接入单元和2#交换接入单元，2#交换单元分别与1#交换接入单元和2#交换接入单元，这六个链路的拥塞情况。
S120、根据当前拥塞情况调整第一类型令牌桶的令牌量。
在实施例中，令牌桶指的是网络设备的内部存储池，令牌指的是以给定速率填充令牌桶的虚拟信息包。在实施例中，第一类型令牌桶指的是整个交换系统的总内部存储池；令牌量指的是第一类型令牌桶所能够填充的虚拟信息包总量。在实施例中，在交换网的当前拥塞情况越拥塞的情况下，第一类型令牌桶的令牌量就越少。在交换网比较拥塞的情况下，为了保证交换网中报文的正常发送和接收，减少第一类型令牌桶中令牌量。
S130、在检测到流量请求指令的情况下，调整流量请求指令所在队列对应的第二类型令牌桶的令牌量。
在实施例中，第二类型令牌桶指的是每个端口级对应令牌桶的内部存储池。在实施例中，第二类型令牌桶比第一类型令牌桶的内部存储池小。一个交换系统中，第二类型令牌桶的数量与端口级个数有关，两者是相同的，并且是一一对应的。每个第二类型令牌桶控制一个端口级。
流量请求指令指的是用户通过端口向交换网发送的报文信息。示例性地，流量请求指令可以为固定周期所需流量的请求指令，比如，可以为每秒20兆带宽。
在实施例中，采用第一类型令牌桶控制所有端口级个数的第二类型令牌桶，并且采用第二类型令牌桶向上级申请授权。在流量请求指令所在队列出现消耗的情况下，调整流量请求指令所在队列对应的第二类型令牌桶的令牌量，而交换系统中其它的第二类型令牌桶的令牌量保持不变，实现了端口级对应的第二类型令牌桶向上级申请授权，从而满足了用户需求，提高了交换系统的服务质 量(Quality of Service，QoS)性能。
在一实施例中，根据当前拥塞情况调整第一类型令牌桶的令牌量，包括：根据预先接收到的交换单元中每个通道的拥塞状态计算得到对应的总拥塞值；根据预设拥塞门限值和总拥塞值确定对应的拥塞等级；根据拥塞等级确定对应的授权下发间隔；按照授权下发间隔调整第一类型令牌桶的令牌量。
在实施例中，每个通道指的是每个交换单元和交换接入单元之间的每条链路。在交换系统中，总拥塞值为交换网络中多个通道对应拥塞值的总和。在根据每个通道的拥塞状态得到对应的总拥塞值之后，将总拥塞值和预先配置的预设拥塞门限值进行比较分析，若总拥塞值达到预设拥塞门限值，即为一个拥塞等级。预设拥塞门限值包括多个，不同的预设拥塞门限值为不同拥塞等级的阈值。示例性地，假设预设拥塞门限值分别为a1、b1和c1，在总拥塞值达到a1的情况下，对应的拥塞等级为A等级；在总拥塞值达到b1的情况下，对应的拥塞等级为B等级；在总拥塞值达到c1的情况下，对应的拥塞等级为C等级。其中，a1＞b1＞c1，相应的，不同拥塞等级对应的拥塞情况，A＞B＞C，即A等级对应的拥塞情况最严重，C等级对应的拥塞情况最轻；也就是说，A等级对应的级别最高，C等级对应的级别最低。
在实施例中，在拥塞等级较高的情况下，为了保证对报文的处理能力，可相应的增大队列的授权下发间隔，以减少队列的授权分发。也就是说，在拥塞等级为A等级的情况下，对应的授权下发间隔最大；在拥塞等级为C等级的情况下，对应的授权下发间隔最小。也就是说，不同的拥塞等级，所配置的授权下发间隔不同。在实施例中，在根据拥塞等级确定交换网络中队列的授权下发间隔之后，再按照授权下发间隔增加或减少第一类型令牌桶的令牌，即调整第一类型令牌桶的令牌量。
在一实施例中，在检测到流量请求指令的情况下，在调整流量请求指令所在队列对应的第二类型令牌桶的令牌量之前，还包括：根据流量请求指令所在队列的序号确定对应第二类型令牌桶的第一门限值、当前桶深度和权重系数；根据第二类型令牌桶的当前桶深度与第一门限值的对比结果，确定第二类型令牌桶对应的排队先进先出(First Input First Output，FIFO)的进出情况。
在实施例中，在检测到流量请求指令的情况下，表征队列授权分发有效或扫描到队列，可根据流量请求指令所在队列的序号选择对应第二类型令牌桶的第一门限值。其中，第一门限值指的是第二类型令牌桶的最低阈值，即在第二类型令牌桶的当前桶深度小于最低阈值的情况下，第二类型令牌桶需进入排队FIFO中等待被服务，即将授权分发有效的队列或所扫描到的队列放入该第二类型令牌桶中。
在一实施例中，调整流量请求指令所在队列对应的第二类型令牌桶的令牌量，包括：在流量请求指令所在队列授权分发有效或扫描到队列的情况下，调整第二类型令牌桶的令牌量。
在实施例中，在第二类型令牌桶对应的队列授权分发有效或扫描到队列的情况下，需通过该队列所在的第二类型令牌桶向上级申请信息，即在第二类型令牌桶处理该队列时，对第二类型令牌桶的当前桶深度执行减操作。
在一实施例中，在排队FIFO中非空且获取到队列的序号的情况下，交换网络拥塞管理方法，还包括：根据队列的序号确定队列所在的第二类型令牌桶的第二门限值、当前桶深度和权重系数；根据权重系数调整第一类型令牌桶的令牌量。
在实施例中，在排队FIFO中非空且能够读取出队列的序号的情况下，使用从排队FIFO中读取的队列的序号选择所在的第二类型令牌桶的第二门限值，并读取出该第二类型令牌桶的当前桶深度和权重系数，并根据权重系数调整第一类型令牌桶所需减少的令牌量。在实施例中，第二类型令牌桶的权重系数用来表征第一类型令牌桶所需减少的令牌量。示例性地，第一类型令牌桶所需减少的令牌量可以与第二类型令牌桶的权重系数相等，也可以成一定比例，对此并不进行限定。比如，在第一类型令牌桶所需减少的令牌量与第二类型令牌桶的权重系数相等，则在确定第二类型令牌桶的权重系数之后，即可算出第一类型令牌桶的令牌量。
在一实施例中，调整流量请求指令所在队列对应的第二类型令牌桶的令牌量，包括：按照第一类型令牌桶的令牌量调整队列对应的第二类型令牌桶的令牌量。
在实施例中，第二类型令牌桶所需增加的令牌量与第一类型令牌桶所需减少的令牌量相同。在确定第一类型令牌桶的令牌量之后，将第一类型令牌桶所需增加的令牌量作为第二类型令牌桶所需减少的令牌量。
在一实施例中，在调整流量请求指令所在队列对应的第二类型令牌桶的令牌量之后，还包括：根据第二类型令牌桶的当前桶深度确定对应的排队FIFO的进出情况；更新第二类型令牌桶的当前桶深度和上报信息。
在实施例中，第二门限值指的是第二类型令牌桶的最高阈值。在实施例中，在第二类型令牌桶的当前桶深度高于第二门限值的情况下，第二类型令牌桶需出排队FIFO，即无需向该第二类型令牌桶中增加授权分发有效或所扫描到的队列。同时，更新第二类型令牌桶的当前桶深度和向上级申请的信息，以重新执行调整第一类型令牌桶的令牌量和第二类型令牌桶的令牌量的操作。
图4是一种向上级申请状态的示意图。如图4所示，通过一个桶来控制所有单播队列的申请，从而导致在拥塞的情况下，真正的端口级授权比例不准确的现象。
图5是本申请实施例提供的一种向上级申请状态的示意图。如图5所示，采用一个第一类型令牌桶控制所有端口级个数的第二类型令牌桶，并通过第二类型令牌桶向上级申请授权，从而在用户配置端口级权重正确的前提下，满足了用户需求，提高了交换系统的QoS性能。
在实施例中，以第一类型令牌桶为大桶，第二类型令牌桶为小桶为例，对向上级申请状态的过程进行说明。在实施例中，在有小桶对应的队列授权分发有效或者扫描到该队列的时候得到本次要操作的该小桶信息，通过对应的队列序号选择对应小桶的正常(normal)门限(即第一门限值)，同时读出该队列对应小桶的桶深度、权重系数等信息，以确认该小桶是否需要进入排队FIFO中等待被服务，同时会更新小桶的桶深度即减操作。排队FIFO中非空且被读出来后得到的队列序号，使用该队列序号判断该小桶选择对应桶的关闭(off)门限(即第二门限值)，同时读出该小桶最新的桶深度、权重系数等信息，根据权重系数知道此时大桶需要减少的令牌量，同时也是该小桶此时应该添加的令牌量。然后，根据小桶的当前桶深度判断该小桶是否还需要再次入排队FIFO还是出排队FIFO。然后，更新小桶的桶深度和向上级申请的信息。
在实施例中，对大桶的加操作可以根据交换网的当前拥塞情况来判断。交换网的拥塞情况是从交换单元中的不同通道接收到的拥塞状态计算出一个总的拥塞值进行确定的，然后根据预先配置的拥塞门限值(即预设拥塞门限值)得到不同的拥塞等级，并为不同拥塞等级配置不同的授权下发间隔，以调整第一类型令牌桶的令牌量。
图6是本申请实施例提供的一种交换网络拥塞管理装置的结构框图。本实施例应用于交换机或路由器等交换网络中出现拥塞的情况。如图6所示，本实施例中的装置包括：获取模块210、第一调整模块220和第二调整模块230。
其中，获取模块210，设置为获取交换网的当前拥塞情况；第一调整模块220，设置为根据所述当前拥塞情况调整第一类型令牌桶的令牌量；第二调整模块230，设置为在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
本实施例提供的交换网络拥塞管理装置设置为实现图3所示实施例的交换网络拥塞管理方法，本实施例提供的交换网络拥塞管理装置实现原理和效果类似，此处不再赘述。
在一实施例中，第一调整模块，包括：
计算单元，设置为根据预先接收到的交换单元中每个通道的拥塞状态计算得到对应的总拥塞值；第一确定单元，设置为根据预设拥塞门限值和所述总拥塞值确定对应的拥塞等级；第二确定单元，设置为根据所述拥塞等级确定对应的授权下发间隔；第一调整单元，设置为按照所述授权下发间隔调整第一类型令牌桶的令牌量。
在一实施例中，交换网络拥塞管理装置，还包括：
第一确定模块，设置为在检测到流量请求指令的情况下，在所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量之前，根据流量请求指令所在队列的序号确定对应第二类型令牌桶的第一门限值、当前桶深度和权重系数；第二确定模块，设置为根据所述第二类型令牌桶的当前桶深度与所述第一门限值的对比结果，确定所述第二类型令牌桶对应的排队FIFO的进出情况。
在一实施例中，第二调整模块，设置为在所述流量请求指令所在队列授权分发有效或扫描到队列的情况下，调整所述第二类型令牌桶的令牌量。
在一实施例中，交换网络拥塞管理装置，还包括：
第三确定模块，设置为在所述排队FIFO中非空且获取到队列的序号的情况下，根据所述队列的序号确定队列所在的第二类型令牌桶的第二门限值、当前桶深度和权重系数；第三调整模块，设置为根据所述权重系数调整第一类型令牌桶的令牌量。
在一实施例中，第二调整模块，还设置为按照所述第一类型令牌桶的令牌量调整所述队列对应的第二类型令牌桶的令牌量。
在一实施例中，交换网络拥塞管理装置，还包括：
第四确定模块，设置为在所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量之后，根据所述第二类型令牌桶的当前桶深度确定对应的排队FIFO的进出情况；更新模块，设置为更新所述第二类型令牌桶的当前桶深度和上报信息。
图7是本申请实施例提供的一种设备的结构示意图。如图7所示，本申请提供的设备，包括：处理器310和存储器320。该设备中处理器310的数量可以是一个或者多个，图7中以一个处理器310为例。该设备中存储器320的数量可以是一个或者多个，图7中以一个存储器320为例。该设备的处理器310和存储器320以通过总线或者其他方式连接，图7中以通过总线连接为例。在该实施例中，该设备为交换接入设备。
存储器320作为一种计算机可读存储介质，可设置为存储软件程序、计算机可执行程序以及模块，如本申请任意实施例的设备对应的程序指令/模块(例如，交换网络拥塞管理装置中的获取模块210、第一调整模块220和第二调整模块230)。存储器320可包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据设备的使用所创建的数据等。此外，存储器320可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器320可包括相对于处理器310远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述提供的设备可设置为执行上述任意实施例提供的交换网络拥塞管理方法，具备相应的功能和效果。
本申请实施例还提供一种包含计算机可执行指令的存储介质，计算机可执行指令在由计算机处理器执行时用于执行一种交换网络拥塞管理方法，该方法包括：获取交换网的当前拥塞情况；根据所述当前拥塞情况调整第一类型令牌桶的令牌量；在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
术语用户设备涵盖任何适合类型的无线用户设备，例如移动电话、便携数据处理装置、便携网络浏览器或车载移动台。
一般来说，本申请的多种实施例可以在硬件或专用电路、软件、逻辑或其任何组合中实现。例如，一些方面可以被实现在硬件中，而其它方面可以被实现在可以被控制器、微处理器或其它计算装置执行的固件或软件中，尽管本申请不限于此。
本申请的实施例可以通过移动装置的数据处理器执行计算机程序指令来实现，例如在处理器实体中，或者通过硬件，或者通过软件和硬件的组合。计算机程序指令可以是汇编指令、指令集架构(Instruction Set Architecture，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码。
本申请附图中的任何逻辑流程的框图可以表示程序步骤，或者可以表示相互连接的逻辑电路、模块和功能，或者可以表示程序步骤与逻辑电路、模块和功能的组合。计算机程序可以存储在存储器上。存储器可以具有任何适合于本地技术环境的类型并且可以使用任何适合的数据存储技术实现，例如但不限于只读存储器(Read-Only Memory，ROM)、随机访问存储器(Random Access Memory，RAM)、光存储器装置和系统(数码多功能光碟(Digital Video Disc， DVD)或光盘(Compact Disk，CD))等。计算机可读介质可以包括非瞬时性存储介质。数据处理器可以是任何适合于本地技术环境的类型，例如但不限于通用计算机、专用计算机、微处理器、数字信号处理器(Digital Signal Processing，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑器件(Field-Programmable Gate Array，FPGA)以及基于多核处理器架构的处理器。

Claims (10)

  1. 一种交换网络拥塞管理方法，包括：
    获取交换网的拥塞情况，根据所述拥塞情况调整第一类型令牌桶的令牌量；
    在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
  2. 根据权利要求1所述的方法，其中，所述根据所述拥塞情况调整第一类型令牌桶的令牌量，包括：
    根据预先接收到的交换单元中多个通道中每个通道的拥塞状态计算得到所述多个通道对应的总拥塞值；
    根据多个预设拥塞门限值和所述总拥塞值确定拥塞等级；
    根据所述拥塞等级确定授权下发间隔；
    按照所述授权下发间隔调整所述第一类型令牌桶的令牌量。
  3. 根据权利要求1所述的方法，其中，在检测到所述流量请求指令的情况下，在所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量之前，还包括：
    根据所述流量请求指令所在队列的序号确定所述第二类型令牌桶的第一门限值和桶深度；
    根据所述第二类型令牌桶的所述桶深度与所述第一门限值的对比结果，确定所述第二类型令牌桶对应的排队先进先出FIFO的进出情况。
  4. 根据权利要求3所述的方法，其中，所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量，包括：
    在所述流量请求指令所在队列的授权分发有效或扫描到所述流量请求指令所在队列的情况下，调整所述第二类型令牌桶的令牌量。
  5. 根据权利要求3所述的方法，其中，在所述排队FIFO中非空且获取到所述排队FIFO中的队列的序号的情况下，还包括：
    根据所述排队FIFO中的队列的序号确定所述排队FIFO中的队列所在的第二类型令牌桶的第二门限值，并确定所述第二门限值的权重系数；
    根据所述权重系数调整所述第一类型令牌桶的令牌量。
  6. 根据权利要求5所述的方法，其中，所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量，包括：
    按照所述第一类型令牌桶的令牌量调整所述队列对应的第二类型令牌桶的 令牌量。
  7. 根据权利要求1所述的方法，在所述调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量之后，还包括：
    根据所述第二类型令牌桶的桶深度确定所述第二类型令牌桶对应的排队FIFO的进出情况；
    根据所述进出情况更新所述第二类型令牌桶的桶深度和上报信息。
  8. 一种交换网络拥塞管理装置，包括：
    获取模块，设置为获取交换网的拥塞情况；
    第一调整模块，设置为根据所述拥塞情况调整第一类型令牌桶的令牌量；
    第二调整模块，设置为在检测到流量请求指令的情况下，调整所述流量请求指令所在队列对应的第二类型令牌桶的令牌量。
  9. 一种设备，包括：
    存储器，以及，至少一个处理器；
    所述存储器，设置为存储至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-7任一项所述的交换网络拥塞管理方法。
  10. 一种存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-7任一项所述的交换网络拥塞管理方法。
PCT/CN2020/129822 2019-11-20 2020-11-18 交换网络拥塞管理方法、装置、设备和存储介质 WO2021098730A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911143444.XA CN112825511A (zh) 2019-11-20 2019-11-20 一种交换网络拥塞管理方法、装置、设备和存储介质
CN201911143444.X 2019-11-20

Publications (1)

Publication Number Publication Date
WO2021098730A1 true WO2021098730A1 (zh) 2021-05-27

Family

ID=75907166

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/129822 WO2021098730A1 (zh) 2019-11-20 2020-11-18 交换网络拥塞管理方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN112825511A (zh)
WO (1) WO2021098730A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114745682A (zh) * 2022-02-28 2022-07-12 联想(北京)有限公司 一种处理方法以及控制面网元
CN114793216A (zh) * 2022-06-22 2022-07-26 北京轻网科技有限公司 令牌管理及信息发送方法、装置、电子设备及存储介质
WO2023072112A1 (zh) * 2021-10-28 2023-05-04 华为技术有限公司 一种报文调度的方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101110753A (zh) * 2006-07-20 2008-01-23 华为技术有限公司 基于拥塞预警的端到端的质量保证方法及系统
CN101159699A (zh) * 2007-11-27 2008-04-09 杭州华三通信技术有限公司 分布式设备交换网带宽动态分配方法及装置
CN101272348A (zh) * 2008-04-30 2008-09-24 杭州华三通信技术有限公司 一种带宽控制的方法和系统
WO2010142227A1 (zh) * 2009-06-12 2010-12-16 中兴通讯股份有限公司 一种用于交换网流量控制的方法和装置
CN104660521A (zh) * 2013-11-20 2015-05-27 华为技术有限公司 一种组播流量控制的方法和装置
US9450881B2 (en) * 2013-07-09 2016-09-20 Intel Corporation Method and system for traffic metering to limit a received packet rate

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101110753A (zh) * 2006-07-20 2008-01-23 华为技术有限公司 基于拥塞预警的端到端的质量保证方法及系统
CN101159699A (zh) * 2007-11-27 2008-04-09 杭州华三通信技术有限公司 分布式设备交换网带宽动态分配方法及装置
CN101272348A (zh) * 2008-04-30 2008-09-24 杭州华三通信技术有限公司 一种带宽控制的方法和系统
WO2010142227A1 (zh) * 2009-06-12 2010-12-16 中兴通讯股份有限公司 一种用于交换网流量控制的方法和装置
US9450881B2 (en) * 2013-07-09 2016-09-20 Intel Corporation Method and system for traffic metering to limit a received packet rate
CN104660521A (zh) * 2013-11-20 2015-05-27 华为技术有限公司 一种组播流量控制的方法和装置

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023072112A1 (zh) * 2021-10-28 2023-05-04 华为技术有限公司 一种报文调度的方法及装置
CN114745682A (zh) * 2022-02-28 2022-07-12 联想(北京)有限公司 一种处理方法以及控制面网元
CN114745682B (zh) * 2022-02-28 2023-08-18 联想(北京)有限公司 一种处理方法以及控制面网元
CN114793216A (zh) * 2022-06-22 2022-07-26 北京轻网科技有限公司 令牌管理及信息发送方法、装置、电子设备及存储介质
CN114793216B (zh) * 2022-06-22 2022-09-23 北京轻网科技有限公司 令牌管理及信息发送方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN112825511A (zh) 2021-05-21

Similar Documents

Publication Publication Date Title
WO2021098730A1 (zh) 交换网络拥塞管理方法、装置、设备和存储介质
US20220329521A1 (en) Methods for distributing software-determined global load information
US10069701B2 (en) Flexible allocation of packet buffers
US9325637B2 (en) System for performing distributed data cut-through
EP2466824B1 (en) Service scheduling method and device
US9185047B2 (en) Hierarchical profiled scheduling and shaping
US7414973B2 (en) Communication traffic management systems and methods
US10986021B2 (en) Flow management in networks
US9166919B2 (en) Reducing headroom
US8081569B2 (en) Dynamic adjustment of connection setup request parameters
EP2575329B1 (en) Proportional bandwidth sharing of the excess part in a MEF Traffic Profile
EP3758409A1 (en) Data traffic processing method and related network device
US20090010165A1 (en) Apparatus and method for limiting packet transmission rate in communication system
JP2006506845A (ja) ルータにおけるパケットに対し論理リンクを選択する方法
US10536385B2 (en) Output rates for virtual output queses
WO2021148020A1 (zh) 调整服务等级的方法、装置、设备及存储介质
US10728156B2 (en) Scalable, low latency, deep buffered switch architecture
WO2021083160A1 (zh) 数据传输的方法和装置
US11695629B2 (en) Method and apparatus for configuring a network parameter
US20240007406A1 (en) Transmission control method and apparatus
US20120127858A1 (en) Method and apparatus for providing per-subscriber-aware-flow qos
US11677673B1 (en) Low latency flow control in data centers
US11012378B2 (en) Methods and apparatus for shared buffer allocation in a transport node
CN114531399B (zh) 一种内存阻塞平衡方法、装置、电子设备和存储介质
CN110661731B (zh) 一种报文处理方法及其装置

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: 20891103

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: 20891103

Country of ref document: EP

Kind code of ref document: A1