WO2014101675A1 - 带宽的分配方法及系统 - Google Patents

带宽的分配方法及系统 Download PDF

Info

Publication number
WO2014101675A1
WO2014101675A1 PCT/CN2013/089419 CN2013089419W WO2014101675A1 WO 2014101675 A1 WO2014101675 A1 WO 2014101675A1 CN 2013089419 W CN2013089419 W CN 2013089419W WO 2014101675 A1 WO2014101675 A1 WO 2014101675A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
bandwidth
child
parent node
parent
Prior art date
Application number
PCT/CN2013/089419
Other languages
English (en)
French (fr)
Inventor
曹登元
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to US14/762,925 priority Critical patent/US20160013986A1/en
Priority to EP13868874.2A priority patent/EP2940951A4/en
Publication of WO2014101675A1 publication Critical patent/WO2014101675A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0896Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling
    • H04L47/60Queue scheduling implementing hierarchical scheduling
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/64Hybrid switching systems
    • H04L12/6418Hybrid transport
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling
    • H04L47/62Queue scheduling characterised by scheduling criteria
    • H04L47/629Ensuring fair share of resources, e.g. weighted fair queuing [WFQ]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • H04L47/78Architectures of resource allocation
    • H04L47/782Hierarchical allocation of resources, e.g. involving a hierarchy of local and centralised entities
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/70Admission control; Resource allocation
    • H04L47/80Actions related to the user profile or the type of traffic
    • H04L47/805QOS or priority aware

Definitions

  • FIG. 1 is a schematic diagram of a basic WFQ scheduling model according to the related art. As shown in Figure 1, the parent node is a scheduling node, and the corresponding bandwidth is allocated to the child nodes according to different weight values of each child node. The specific bandwidth allocation algorithm can adopt different implementation manners.
  • the bandwidth ratio of the m nodes is Wm/(W0+Wl+...+Wm+...+Wn).
  • the parent node is a port of the device (which may include: a physical port or a logical port), and the child node corresponds to a specific physical queue; for the HQOS service, depending on different application scenarios, the parent node Both the child and the child nodes can be any type of business match value.
  • the HQOS service is multi-layered, the simple WFQ model cannot be directly applied. Moreover, there is a possibility that the services between multiple levels are not configured, and the ordinary WFQ model cannot be satisfied.
  • the embodiments of the present invention provide a bandwidth allocation method and system, so as to at least solve the problem that the basic WFQ scheduling model in the related art cannot be applied to the HQOS service.
  • a bandwidth allocation method is provided.
  • the bandwidth allocation method according to the embodiment of the present invention includes: the child node receives the first bandwidth allocated by the parent node for the child node, wherein the first bandwidth is allocated by the parent node according to the weight value of the child node; The weight value of each of the one or more nodes of the child node allocates the first bandwidth.
  • the method further includes: the parent node acquires the total bandwidth to be allocated; the parent node determines the child node attached to the parent node, and according to The weight value of the child node allocates the first bandwidth to the child node from the total bandwidth.
  • the method further includes: the parent node receives the parent node to be attached The node is the second bandwidth allocated by the parent node, wherein the second bandwidth is allocated by the parent node according to the weight value of the parent node; the parent node allocates the first bandwidth according to the weight value of the child node.
  • the child node allocates the first bandwidth according to the weight value of each node of one or more nodes attached to the child node, including: the child node determines one or more nodes attached to the child node; The node separately obtains the weight values of one or more nodes, and sequentially allocates the first bandwidth according to the weight values of each of the one or more nodes.
  • the service type represented by the parent node or the child node is one of the following: a physical port, a tunnel, and a pseudowire.
  • a bandwidth allocation system is provided.
  • a bandwidth allocation system includes: a child node; the child node includes: a first receiving module, configured to receive a first bandwidth allocated by the parent node for the child node, where the first bandwidth is a parent node according to the child node
  • the first allocation module is configured to allocate the first bandwidth according to the weight value of each of the one or more nodes attached to the child node.
  • the system further includes: a parent node; the parent node includes: an acquiring module, configured to acquire a total bandwidth to be allocated when the parent node is a root node; and a second allocation module, configured to determine a child attached to the parent node a node, and assigning a first bandwidth to the child node from the total bandwidth according to the weight value of the child node.
  • the parent node includes: a second receiving module, configured to receive, when the parent node is a node other than the root node, the leaf node, and the parent node of the leaf node, receive the node that the parent node is attached to the parent node.
  • the first allocation module comprises: a determining unit, configured to determine one or more nodes attached to the child node; and an allocating unit configured to respectively obtain weight values of one or more nodes, and sequentially follow one or more The weight value of each node in the nodes allocates the first bandwidth.
  • the service type represented by the parent node or the child node is one of the following: a physical port, a tunnel, and a pseudowire.
  • the child node receives the weight of the parent node according to the weight value of the child node, and the child node assigns a weight according to the weight of each node of the one or more nodes attached to the child node.
  • the value allocates the first bandwidth, which solves the problem that the basic WFQ scheduling model in the related art cannot be applied to the HQOS service.
  • the problem is further applicable to WFQ scheduling in multi-level and multi-service scenarios, providing a flexible bandwidth allocation method for multi-user and multi-service scenarios.
  • FIG. 2 is a flowchart of a bandwidth allocation method according to an embodiment of the present invention
  • FIG. 3 is a bandwidth allocation method according to a preferred embodiment of the present invention.
  • Figure 4 is a block diagram showing the structure of a bandwidth allocation system according to an embodiment of the present invention;
  • Figure 5 is a block diagram showing the structure of a bandwidth allocation system according to a preferred embodiment of the present invention;
  • Figure 6 is a block diagram of a preferred embodiment of the present invention. Schematic diagram of the system operation architecture. BEST MODE FOR CARRYING OUT THE INVENTION
  • the present invention will be described in detail with reference to the accompanying drawings. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.
  • Step S202 The child node receives a first bandwidth allocated by the parent node for the child node, where the first bandwidth is allocated by the parent node according to the weight value of the child node;
  • Step S204 The child node allocates the first bandwidth according to the weight value of each node of one or more nodes attached to the child node.
  • the basic WFQ scheduling model cannot be applied to the HQOS service.
  • the child node receives the first node according to the weight value of the child node according to the weight value of the child node; the child node is according to each of one or more nodes attached to the child node.
  • the weight value of the node allocates the first bandwidth, that is, the multi-level and basic WFQ model characteristics based on HQOS, based on the basic WFQ scheduling model.
  • a hierarchical WFQ scheduling model is provided, which solves the problem that the basic WFQ scheduling model in the related art cannot be applied to the HQOS service, and is applicable to the WFQ scheduling in the multi-layer and multi-service scenarios, and is a multi-user multi-service scenario. Provide flexible bandwidth allocation methods.
  • the service type represented by the parent node or the child node may be one of the following: but not limited to: a physical port, a tunnel, and a pseudowire. It should be noted that the service type represented by the parent node or the child node may also be: a virtual local area network and a virtual interface, as long as it is a forwarding entity supported by the communication device.
  • the child node may further include the following operations before receiving the first bandwidth allocated by the parent node in step S202: Step S1: the parent node acquires the total bandwidth to be allocated; Step S2: the parent node determines The child node of the parent node is attached, and the first bandwidth is allocated to the child node from the total bandwidth according to the weight value of the child node.
  • the technical solution provided by the present invention may include: 1 root node, n leaf nodes, n virtual WFQ classes (corresponding to the above child nodes); a root node (corresponding to the above parent node), used in According to the total bandwidth to be allocated and the weight value of each virtual WFQ class attached to the root node, bandwidth is allocated for each virtual WFQ class in turn; the virtual WFQ class is connected to the virtual WFQ class according to the acquired bandwidth.
  • the weight values of the leaf nodes are assigned different bandwidths to the respective leaf nodes; each leaf node receives the bandwidth allocated by the virtual WFQ class.
  • Step S3 Parent node Receiving, by the node to which the parent node is attached, a second bandwidth allocated by the parent node, where the second bandwidth is allocated by the parent node according to the weight value of the parent node;
  • Step S4 the parent node is weighted according to the child node The value is assigned to the child node by the first bandwidth.
  • the root node allocates bandwidth for each virtual WFQ class according to the total bandwidth to be allocated and the weight value of each virtual WFQ class attached to the root node; the virtual WFQ class according to the acquired bandwidth, according to the obtained bandwidth
  • the weight value of the node connected to the virtual WFQ class allocates different bandwidth to each node, and the layer is progressive, until the virtual WFQ class attached by the parent node allocates bandwidth according to the weight value of the parent node; second, the parent node And then assigning bandwidth to the child node according to the weight value of the child node; then, the child node is further connected according to the child node
  • the weight value of each node is allocated bandwidth for each node in turn until it is assigned to the leaf node, and each leaf node receives the bandwidth allocated by the virtual WFQ class.
  • the child node allocates the first bandwidth according to the weight value of each node of one or more nodes attached to the child node, which may include the following processing steps: Step S5: determining the hook of the child node One or more nodes in the child node; Step S6: The child nodes respectively obtain weight values of one or more nodes, and sequentially allocate the first bandwidth according to weight values of each of the one or more nodes.
  • Step S5 determining the hook of the child node One or more nodes in the child node
  • Step S6 The child nodes respectively obtain weight values of one or more nodes, and sequentially allocate the first bandwidth according to weight values of each of the one or more nodes.
  • Step S302 Applying a hardware scheduling resource to create a root node
  • Step S304 Applying a software resource, creating 0 to n virtual WFQ scheduling classes
  • Step S306 Applying hardware scheduling resources, Create a 0 to n leaf nodes
  • Step S308 Set a total bandwidth to be allocated by the root node
  • Step S310 Set a weight of the WFQ scheduling class and a parent node to which the WFQ scheduling class is attached
  • Step S312 Determine whether the parent node is a root If yes, go to step S314; if no, go to step S316; Step S314: If the parent node is the root node, then connect the virtual WFQ scheduling class to the root node; continue to step S318;
  • Step S316 If the parent node is another virtual WFQ class, the virtual WFQ scheduling class is attached to the other virtual WFQ class; proceed to step S318;
  • Step S318 Configure the weight of the leaf node
  • the bandwidth allocation system may include: a child node 10; the child node 10 may include: a first receiving module 100, configured to receive a first bandwidth allocated by the parent node for the child node, where the first bandwidth The parent node is assigned according to the weight value of the child node; the first allocating module 102 is configured to allocate the first bandwidth according to the weight value of each node of one or more nodes attached to the child node.
  • a first receiving module 100 configured to receive a first bandwidth allocated by the parent node for the child node, where the first bandwidth The parent node is assigned according to the weight value of the child node
  • the first allocating module 102 is configured to allocate the first bandwidth according to the weight value of each node of one or more nodes attached to the child node.
  • the system may further include: a parent node 20; the parent node 20 may include: an obtaining module 200, configured to acquire a total bandwidth to be allocated when the parent node is a root node; and a second allocation module 202.
  • the parent node 20 may include: a second receiving module 204, configured to receive the parent node when the parent node is a node other than the root node, the leaf node, and the parent node of the leaf node The second bandwidth allocated by the node to which the parent node is assigned, wherein the second bandwidth is allocated by the parent node according to the weight value of the parent node; the third allocation module 206 is set to be based on the weight value of the child node.
  • the child node allocates the first bandwidth.
  • the foregoing first allocating module 102 may include: a determining unit 1020, configured to determine one or more nodes that are attached to the child node; and an allocating unit 1022, configured to acquire one or more respectively The weight value of the node, and the first bandwidth is allocated in turn according to the weight value of each node in one or more nodes.
  • FIG. 6 is a schematic illustration of a system operation architecture in accordance with a preferred embodiment of the present invention. As shown
  • the virtual WFQ scheduling class can implement the creation of a flexible scheduling model according to specific needs.
  • the unit of the above total bandwidth may be one of the following: kilobits per second (Kbit/s), megabits per second (Mbit/s), gigabits per second (Gbit/s).
  • the virtual WFQ class can be directly attached to the root node. If the parent node is a virtual WFQ class, the virtual WFQ class can be attached to other virtual WFQ classes. Similarly, if the parent node of the leaf node is the root node, the leaf node can be directly attached to the root node; and if the parent node of the leaf node is a virtual WFQ class, the leaf node can be attached to the virtual WFQ class.
  • the basic WFQ scheduling model in the related art cannot be applied to The problem of the HQOS service is applicable to the WFQ scheduling in the multi-layer and multi-service scenarios, and provides a flexible bandwidth allocation method for the multi-user and multi-service scenarios.
  • the above modules or steps of the present invention can be implemented by a general-purpose computing device, which can be concentrated on a single computing device or distributed over a network composed of multiple computing devices.
  • the computing device may be implemented by program code executable by the computing device, such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein.
  • the steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps are fabricated as a single integrated circuit module.
  • the invention is not limited to any specific combination of hardware and software.
  • the above is only the preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes can be made to the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.
  • Industrial Applicability The technical solution provided by the embodiments of the present invention can be applied to the field of communications, and solves the basics in the related art.
  • the WFQ scheduling model cannot be applied to the HQOS service problem, and is applicable to WFQ scheduling in multi-layer and multi-service scenarios, and provides a flexible bandwidth allocation method for multi-user and multi-service scenarios.

Landscapes

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

Abstract

本发明公开了一种带宽的分配方法及系统,在上述方法中,子节点接收父节点为子节点分配的第一带宽,其中,第一带宽是父节点根据子节点的权重值分配的;子节点根据挂接在该子节点的一个或多个节点中每个节点的权重值对第一带宽进行分配。根据本发明提供的技术方案,适用于多层次和多业务场景下的WFQ调度,为多用户多业务场景提供灵活的带宽分配方法。

Description

带宽的分配方法及系统 技术领域 本发明涉及通信领域, 具体而言, 涉及一种带宽的分配方法及系统。 背景技术 在通信领域中, 加权平均队列 (Weight Fair Queue, 简称为 WFQ) 是一种基于权 重的公平队列调度, 其广泛应用于服务质量(Quality of Service, 简称为 QOS) 以及层 次服务质量 (Hierarchy Quality of Service, 简称为 HQOS) 业务, 提供各种调度模型。 图 1是根据相关技术的基本 WFQ调度模型的示意图。 如图 1所示, 父节点是一个调 度节点, 按照每个子节点的不同权重值, 分配相应的带宽给子节点。 具体的带宽分配 算法可以采用不同的实现方式, 其中, 最常用的实现方式为: m节点的带宽占比为 Wm/(W0+Wl+...+Wm+...+Wn)。 对于 QOS而言, 父节点是设备的一个端口 (可以包 括: 物理端口或者逻辑端口), 而子节点则与具体的物理队列相对应; 对于 HQOS业 务而言, 取决于不同的应用场景, 父节点和子节点均可以是任意类型的业务匹配值。 但是, 由于 HQOS业务是多层次的, 简单的 WFQ模型无法直接应用; 而且, 多层次 之间的业务存在不种配置的可能性, 普通的 WFQ模型无法满足。 发明内容 本发明实施例提供了一种带宽的分配方法及系统, 以至少解决相关技术中的基本 WFQ调度模型无法适用于 HQOS业务的问题。 根据本发明实施例的一个方面, 提供了一种带宽的分配方法。 根据本发明实施例的带宽的分配方法包括: 子节点接收父节点为子节点分配的第 一带宽, 其中, 第一带宽是父节点根据子节点的权重值分配的; 子节点根据挂接在该 子节点的一个或多个节点中每个节点的权重值对第一带宽进行分配。 优选地, 如果父节点为根节点, 在子节点接收父节点分配的第一带宽之前, 还包 括: 父节点获取待分配的总带宽; 父节点确定挂接在该父节点的子节点, 并根据子节 点的权重值从总带宽中为子节点分配第一带宽。 优选地, 如果父节点为除根节点、 叶子节点以及叶子节点的父节点之外的其他节 点, 在子节点接收父节点分配的第一带宽之前, 还包括: 父节点接收该父节点所挂接 的节点为父节点分配的第二带宽, 其中, 第二带宽是父节点所挂接的节点根据父节点 的权重值分配的; 父节点根据子节点的权重值为子节点分配第一带宽。 优选地, 子节点根据挂接在该子节点的一个或多个节点中每个节点的权重值对第 一带宽进行分配包括: 子节点确定挂接在该子节点的一个或多个节点; 子节点分别获 取一个或多个节点的权重值, 并依次按照一个或多个节点中每个节点的权重值对第一 带宽进行分配。 优选地, 父节点或者子节点所代表的业务类型为以下之一: 物理端口、 隧道、 伪 线。 根据本发明实施例的另一方面, 提供了一种带宽的分配系统。 根据本发明实施例的带宽的分配系统包括: 子节点; 该子节点包括: 第一接收模 块, 设置为接收父节点为子节点分配的第一带宽, 其中, 第一带宽是父节点根据子节 点的权重值分配的; 第一分配模块, 设置为根据挂接在该子节点的一个或多个节点中 每个节点的权重值对第一带宽进行分配。 优选地, 上述系统还包括: 父节点; 父节点包括: 获取模块, 设置为在父节点为 根节点时, 获取待分配的总带宽; 第二分配模块, 设置为确定挂接在父节点的子节点, 并根据子节点的权重值从总带宽中为子节点分配第一带宽。 优选地, 父节点包括: 第二接收模块, 设置为在父节点为除根节点、 叶子节点以 及叶子节点的父节点之外的其他节点时, 接收该父节点所挂接的节点为父节点分配的 第二带宽, 其中, 第二带宽是父节点所挂接的节点根据父节点的权重值分配的; 第三 分配模块, 设置为根据子节点的权重值为子节点分配第一带宽。 优选地, 第一分配模块包括: 确定单元, 设置为确定挂接在该子节点的一个或多 个节点; 分配单元, 设置为分别获取一个或多个节点的权重值, 并依次按照一个或多 个节点中每个节点的权重值对第一带宽进行分配。 优选地, 父节点或者子节点所代表的业务类型为以下之一: 物理端口、 隧道、 伪 线。 通过本发明实施例, 采用子节点接收父节点根据该子节点的权重值为该子节点分 配的第一带宽; 子节点根据挂接在该子节点的一个或多个节点中每个节点的权重值对 第一带宽进行分配, 解决了相关技术中的基本 WFQ调度模型无法适用于 HQOS业务 的问题, 进而适用于多层次和多业务场景下的 WFQ调度, 为多用户多业务场景提供 灵活的带宽分配方法。 附图说明 此处所说明的附图用来提供对本发明实施例的进一步理解,构成本申请的一部分, 本发明的示意性实施例及其说明用于解释本发明, 并不构成对本发明的不当限定。 在 附图中- 图 1是根据相关技术的基本 WFQ调度模型的示意图; 图 2是根据本发明实施例的带宽的分配方法的流程图; 图 3是根据本发明优选实施例的带宽的分配方法的流程图; 图 4是根据本发明实施例的带宽的分配系统的结构框图; 图 5是根据本发明优选实施例的带宽的分配系统的结构框图; 以及 图 6是根据本发明优选实施例的系统运行架构的示意图。 具体实施方式 下文中将参考附图并结合实施例来详细说明本发明。 需要说明的是, 在不冲突的 情况下, 本申请中的实施例及实施例中的特征可以相互组合。 图 2是根据本发明实施例的带宽的分配方法的流程图。 如图 2所示, 该方法可以 包括以下处理步骤: 步骤 S202: 子节点接收父节点为子节点分配的第一带宽, 其中, 第一带宽是父节 点根据子节点的权重值分配的; 步骤 S204: 子节点根据挂接在该子节点的一个或多个节点中每个节点的权重值对 第一带宽进行分配。 相关技术中, 基本 WFQ调度模型无法适用于 HQOS业务。 采用如图 2所示的方 法, 采用子节点接收父节点根据该子节点的权重值为该子节点分配的第一带宽; 子节 点根据挂接在该子节点的一个或多个节点中每个节点的权重值对第一带宽进行分配, 即基于 HQOS的多层次和基本的 WFQ模型特性, 在基本 WFQ调度模型的基础之上, 提供一种层次化的 WFQ调度模型,由此解决了相关技术中的基本 WFQ调度模型无法 适用于 HQOS业务的问题, 进而适用于多层次和多业务场景下的 WFQ调度, 为多用 户多业务场景提供灵活的带宽分配方法。 在优选实施过程中, 上述父节点或者子节点所代表的业务类型可以为但不限于以 下之一: 物理端口、 隧道、 伪线。 需要说明的是, 上述父节点或者子节点所代表的业务类型还可以是: 虚拟局域网、 虚拟接口, 只要是通信设备支持的转发实体即可。 优选地, 如果父节点为根节点, 在步骤 S202, 子节点接收父节点分配的第一带宽 之前, 还可以包括以下操作: 步骤 S1 : 父节点获取待分配的总带宽; 步骤 S2: 父节点确定挂接在该父节点的子节点, 并根据子节点的权重值从总带宽 中为子节点分配第一带宽。 在优选实施例中, 本发明提供的技术方案可以包括: 1个根节点, n个叶子节点, n个虚拟 WFQ类(相当于上述子节点); 根节点 (相当于上述父节点), 用于根据待分 配的总带宽和挂接在根节点的各个虚拟 WFQ类的权重值,依次为每个虚拟 WFQ类分 配带宽; 虚拟 WFQ类则根据获取到的带宽, 按照挂接在该虚拟 WFQ类的叶子节点的 权重值分配不同的带宽给各个叶子节点; 各个叶子节点接收虚拟 WFQ类分配的带宽。 优选地, 如果父节点为除根节点、 叶子节点以及叶子节点的父节点之外的其他节 点, 在步骤 S202子节点接收父节点分配的第一带宽之前, 还可以包括以下步骤: 步骤 S3: 父节点接收该父节点所挂接的节点为父节点分配的第二带宽, 其中, 第 二带宽是父节点所挂接的节点根据父节点的权重值分配的; 步骤 S4: 父节点根据子节点的权重值为子节点分配第一带宽。 在优选实施例中, 根节点根据待分配的总带宽和挂接在根节点的各个虚拟 WFQ 类的权重值, 依次为每个虚拟 WFQ类分配带宽; 虚拟 WFQ类则根据获取到的带宽, 按照挂接在该虚拟 WFQ类的节点的权重值分配不同的带宽给各个节点, 层层递进, 直至父节点挂接的虚拟 WFQ类根据父节点的权重值为父节点分配带宽; 其次, 父节 点再根据子节点的权重值为子节点分配带宽; 然后, 子节点再根据挂接在该子节点的 各个节点的权重值依次为每个节点分配带宽, 直至分配至叶子节点, 各个叶子节点接 收虚拟 WFQ类分配的带宽。 优选地,在步骤 S204中,子节点根据挂接在该子节点的一个或多个节点中每个节 点的权重值对第一带宽进行分配可以包括以下处理步骤: 步骤 S5 : 子节点确定挂接在该子节点的一个或多个节点; 步骤 S6: 子节点分别获取一个或多个节点的权重值, 并依次按照一个或多个节点 中每个节点的权重值对第一带宽进行分配。 下面结合图 3所示的优选实施方式对上述优选实施过程做进一步的描述。 图 3是根据本发明优选实施例的带宽的分配方法的流程图。 如图 3所示, 该流程 可以包括以下步骤: 步骤 S302: 申请硬件调度资源, 创建根节点; 步骤 S304: 申请软件资源, 创建 0到 n个虚拟 WFQ调度类; 步骤 S306: 申请硬件调度资源, 创建 0到 n个叶子节点; 步骤 S308: 设置根节点待分配的总带宽; 步骤 S310: 设置 WFQ调度类的权重以及该 WFQ调度类所挂接的父节点; 步骤 S312: 判断父节点是否为根节点; 如果是, 继续执行步骤 S314; 如果否, 则转到步骤 S316; 步骤 S314: 如果父节点为根节点, 则将上述虚拟 WFQ调度类挂接到根节点上; 继续执行步骤 S318; 步骤 S316: 如果父节点为其他虚拟 WFQ类, 则将上述虚拟 WFQ调度类挂接到 其他虚拟 WFQ类上; 继续执行步骤 S318; 步骤 S318: 配置叶子节点的权重以及叶子节点所挂接的父节点; 步骤 S320: 判断父节点是否为根节点; 如果是, 继续执行步骤 S322; 如果否, 则转到步骤 S324; 步骤 S322: 如果父节点为根节点, 则将上述叶子节点直接挂接到根节点上; 步骤 S324: 如果父节点为其他虚拟 WFQ类, 则将上述叶子节点挂接到其他虚拟 WFQ类上。 图 4是根据本发明实施例的带宽的分配系统的结构框图。 如图 4所示, 该带宽的 分配系统可以包括: 子节点 10; 该子节点 10可以包括: 第一接收模块 100, 设置为接 收父节点为子节点分配的第一带宽, 其中, 第一带宽是父节点根据子节点的权重值分 配的; 第一分配模块 102, 设置为根据挂接在该子节点的一个或多个节点中每个节点 的权重值对第一带宽进行分配。 采用如图 4 所示的系统, 解决了相关技术中的基本 WFQ 调度模型无法适用于 HQOS业务的问题, 进而适用于多层次和多业务场景下的 WFQ调度, 为多用户多业 务场景提供灵活的带宽分配方法。 在优选实施过程中, 上述父节点或者子节点所代表的业务类型可以为但不限于以 下之一: 物理端口、 隧道、 伪线。 优选地, 如图 5所示, 上述系统还可以包括: 父节点 20; 父节点 20可以包括: 获取模块 200,设置为在父节点为根节点时,获取待分配的总带宽;第二分配模块 202, 设置为确定挂接在父节点的子节点, 并根据子节点的权重值从总带宽中为子节点分配 第一带宽。 优选地, 如图 5所示, 父节点 20可以包括: 第二接收模块 204, 设置为在父节点 为除根节点、 叶子节点以及叶子节点的父节点之外的其他节点时, 接收该父节点所挂 接的节点为父节点分配的第二带宽, 其中, 第二带宽是父节点所挂接的节点根据父节 点的权重值分配的; 第三分配模块 206, 设置为根据子节点的权重值为子节点分配第 一带宽。 优选地, 如图 5所示, 上述第一分配模块 102可以包括: 确定单元 1020, 设置为 确定挂接在该子节点的一个或多个节点; 分配单元 1022, 设置为分别获取一个或多个 节点的权重值,并依次按照一个或多个节点中每个节点的权重值对第一带宽进行分配。 在优选实施例中, 图 6是根据本发明优选实施例的系统运行架构的示意图。 如图
6所示, 可以根据创建参数, 创建 1个根节点, 0到 n个虚拟 WFQ调度类以及创建 0 到 n个叶子节点; 同时还可以根据配置参数, 设置根节点待分配的总带宽, 配置虚拟 WFQ 类的权重值和选择需要挂接的父节点以及配置子节点的权重值和选择需要挂接 的父节点。 虚拟 WFQ调度类可以按照特定需求实现灵活的调度模型的创建。 上述总 带宽的单位可以为以下之一: 千比特 /秒 (Kbit/s )、 兆比特 /秒 (Mbit/s)、 吉比特 /秒 (Gbit/s)。 如果上述父节点为根节点, 则虚拟 WFQ类可以直接挂接到根节点上; 如 果上述父节点为虚拟 WFQ类,则虚拟 WFQ类可以挂接到其他虚拟 WFQ类上。同理, 如果叶子节点的父节点为根节点, 则叶子节点可以直接挂接到根节点上; 而如果叶子 节点的父节点为虚拟 WFQ类, 则叶子节点可以挂接到该虚拟 WFQ类上。 从以上的描述中, 可以看出, 上述实施例实现了如下技术效果 (需要说明的是这 些效果是某些优选实施例可以达到的效果): 解决了相关技术中的基本 WFQ调度模型 无法适用于 HQOS业务的问题, 进而适用于多层次和多业务场景下的 WFQ调度, 为 多用户多业务场景提供灵活的带宽分配方法。 显然, 本领域的技术人员应该明白, 上述的本发明的各模块或各步骤可以用通用 的计算装置来实现, 它们可以集中在单个的计算装置上, 或者分布在多个计算装置所 组成的网络上, 可选地, 它们可以用计算装置可执行的程序代码来实现, 从而, 可以 将它们存储在存储装置中由计算装置来执行, 并且在某些情况下, 可以以不同于此处 的顺序执行所示出或描述的步骤, 或者将它们分别制作成各个集成电路模块, 或者将 它们中的多个模块或步骤制作成单个集成电路模块来实现。 这样, 本发明不限制于任 何特定的硬件和软件结合。 以上所述仅为本发明的优选实施例而已, 并不用于限制本发明, 对于本领域的技 术人员来说, 本发明可以有各种更改和变化。 凡在本发明的精神和原则之内, 所作的 任何修改、 等同替换、 改进等, 均应包含在本发明的保护范围之内。 工业实用性 本发明实施例提供的技术方案可以应用于通信领域, 解决了相关技术中的基本
WFQ调度模型无法适用于 HQOS业务的问题, 进而适用于多层次和多业务场景下的 WFQ调度, 为多用户多业务场景提供灵活的带宽分配方法。

Claims

权 利 要 求 书
1. 一种带宽的分配方法, 包括:
子节点接收父节点为所述子节点分配的第一带宽, 其中, 所述第一带宽是 所述父节点根据所述子节点的权重值分配的;
所述子节点根据挂接在该子节点的一个或多个节点中每个节点的权重值对 所述第一带宽进行分配。
2. 根据权利要求 1所述的方法, 其中, 如果所述父节点为根节点, 在所述子节点 接收所述父节点分配的所述第一带宽之前, 还包括:
所述父节点获取待分配的总带宽;
所述父节点确定挂接在该父节点的所述子节点, 并根据所述子节点的权重 值从所述总带宽中为所述子节点分配所述第一带宽。
3. 根据权利要求 1所述的方法, 其中, 如果所述父节点为除根节点、 叶子节点以 及所述叶子节点的父节点之外的其他节点, 在所述子节点接收所述父节点分配 的所述第一带宽之前, 还包括:
所述父节点接收该父节点所挂接的节点为所述父节点分配的第二带宽, 其 中,所述第二带宽是所述父节点所挂接的节点根据所述父节点的权重值分配的; 所述父节点根据所述子节点的权重值为所述子节点分配所述第一带宽。
4. 根据权利要求 1所述的方法, 其中, 所述子节点根据挂接在该子节点的一个或 多个节点中每个节点的权重值对所述第一带宽进行分配包括:
所述子节点确定挂接在该子节点的所述一个或多个节点;
所述子节点分别获取所述一个或多个节点的权重值, 并依次按照所述一个 或多个节点中每个节点的权重值对所述第一带宽进行分配。
5. 根据权利要求 1至 4中任一项所述的方法, 其中, 所述父节点或者所述子节点 所代表的业务类型为以下之一:
物理端口、 隧道、 伪线。
6. 一种带宽的分配系统, 包括: 子节点; 所述子节点包括:
第一接收模块, 设置为接收父节点为所述子节点分配的第一带宽, 其中, 所述第一带宽是所述父节点根据所述子节点的权重值分配的;
第一分配模块, 设置为根据挂接在该子节点的一个或多个节点中每个节点 的权重值对所述第一带宽进行分配。 根据权利要求 6所述的系统, 其中, 所述系统还包括: 所述父节点; 所述父节点包括:
获取模块, 设置为在所述父节点为根节点时, 获取待分配的总带宽; 第二分配模块, 设置为确定挂接在所述父节点的所述子节点, 并根据所述 子节点的权重值从所述总带宽中为所述子节点分配所述第一带宽。 根据权利要求 6所述的系统, 其中,
所述父节点包括:
第二接收模块, 设置为在所述父节点为除根节点、 叶子节点以及所述叶子 节点的父节点之外的其他节点时, 接收该父节点所挂接的节点为所述父节点分 配的第二带宽, 其中, 所述第二带宽是所述父节点所挂接的节点根据所述父节 点的权重值分配的;
第三分配模块, 设置为根据所述子节点的权重值为所述子节点分配所述第 一带宽。 根据权利要求 6所述的系统, 其中, 所述第一分配模块包括:
确定单元, 设置为确定挂接在该子节点的所述一个或多个节点; 分配单元, 设置为分别获取所述一个或多个节点的权重值, 并依次按照所 述一个或多个节点中每个节点的权重值对所述第一带宽进行分配。 根据权利要求 6至 9中任一项所述的系统, 其中, 所述父节点或者所述子节点 所代表的业务类型为以下之一:
物理端口、 隧道、 伪线。
PCT/CN2013/089419 2012-12-26 2013-12-13 带宽的分配方法及系统 WO2014101675A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US14/762,925 US20160013986A1 (en) 2012-12-26 2013-12-13 Bandwidth Allocation Method and System
EP13868874.2A EP2940951A4 (en) 2012-12-26 2013-12-13 METHOD AND SYSTEM FOR ALLOCATING BANDWIDTH

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210574894.6 2012-12-26
CN2012105748946A CN103067308A (zh) 2012-12-26 2012-12-26 带宽的分配方法及系统

Publications (1)

Publication Number Publication Date
WO2014101675A1 true WO2014101675A1 (zh) 2014-07-03

Family

ID=48109776

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/089419 WO2014101675A1 (zh) 2012-12-26 2013-12-13 带宽的分配方法及系统

Country Status (4)

Country Link
US (1) US20160013986A1 (zh)
EP (1) EP2940951A4 (zh)
CN (1) CN103067308A (zh)
WO (1) WO2014101675A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103067308A (zh) * 2012-12-26 2013-04-24 中兴通讯股份有限公司 带宽的分配方法及系统
US20170195237A1 (en) * 2015-12-30 2017-07-06 Akamai Technologies, Inc. Distributed quality-of-service (QoS) mechanism in an overlay network having edge regions
CN107483361B (zh) * 2016-06-08 2022-04-15 中兴通讯股份有限公司 一种调度模型构建方法和装置
CN110213620B (zh) * 2018-02-28 2021-10-19 阿里巴巴(中国)有限公司 带宽分配方法及装置
CN108601086B (zh) * 2018-04-23 2022-12-23 重庆人文科技学院 一种带宽自适应方法
CN112929294A (zh) * 2019-12-06 2021-06-08 华为技术有限公司 一种报文调度方法及装置
CN112035623B (zh) * 2020-09-11 2023-08-04 杭州海康威视数字技术股份有限公司 智能问答方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0753979A1 (en) * 1995-07-13 1997-01-15 International Business Machines Corporation Routing method and system for a high speed packet switching network
CN101523372A (zh) * 2006-10-05 2009-09-02 澳大利亚国家Ict有限公司 分散式多用户在线环境
CN101667974A (zh) * 2009-10-12 2010-03-10 中兴通讯股份有限公司 一种实现分层服务质量的方法及网络处理器
CN103067308A (zh) * 2012-12-26 2013-04-24 中兴通讯股份有限公司 带宽的分配方法及系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6816456B1 (en) * 2000-02-04 2004-11-09 At&T Corp. Methods and apparatus for network use optimization
US7260635B2 (en) * 2000-03-21 2007-08-21 Centrisoft Corporation Software, systems and methods for managing a distributed network
US7339953B2 (en) * 2002-08-30 2008-03-04 Redback Networks, Inc. Surplus redistribution for quality of service classification for packet processing
US7369495B1 (en) * 2004-09-07 2008-05-06 Juniper Networks, Inc. Method and apparatus for shared shaping
US7453804B1 (en) * 2005-02-08 2008-11-18 Packeteer, Inc. Aggregate network resource utilization control scheme
CN101035389A (zh) * 2006-03-08 2007-09-12 上海交通大学 在无源光网络的远端设备内进行带宽分配的系统和方法
US7969886B1 (en) * 2008-12-15 2011-06-28 Tejas Israel Ltd Bandwidth allocation for hierarchical telecommunications networks
CN101583160B (zh) * 2009-06-19 2011-08-24 中兴通讯股份有限公司 一种实现分层服务质量业务的装置及方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0753979A1 (en) * 1995-07-13 1997-01-15 International Business Machines Corporation Routing method and system for a high speed packet switching network
CN101523372A (zh) * 2006-10-05 2009-09-02 澳大利亚国家Ict有限公司 分散式多用户在线环境
CN101667974A (zh) * 2009-10-12 2010-03-10 中兴通讯股份有限公司 一种实现分层服务质量的方法及网络处理器
CN103067308A (zh) * 2012-12-26 2013-04-24 中兴通讯股份有限公司 带宽的分配方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP2940951A4 *

Also Published As

Publication number Publication date
EP2940951A1 (en) 2015-11-04
US20160013986A1 (en) 2016-01-14
CN103067308A (zh) 2013-04-24
EP2940951A4 (en) 2016-08-31

Similar Documents

Publication Publication Date Title
WO2014101675A1 (zh) 带宽的分配方法及系统
WO2019149016A1 (zh) 网络切片创建方法、系统、网络设备及存储介质
JP4995808B2 (ja) データネットワークを通して強化されたコンテンツ配信を行うための方法及び装置
Lu et al. Data-oriented task scheduling in fixed-and flexible-grid multilayer inter-DC optical networks: A comparison study
JP5260677B2 (ja) ネットワーク内の改善されたリソース割当て計画
CN108462999B (zh) 一种进行资源分配的方法和设备
RU2643666C2 (ru) Способ и устройство для управления авторизацией виртуальной очереди вывода, а также компьютерный носитель информации
WO2015096680A1 (zh) 一种节点分配方法和控制中心
US11929911B2 (en) Shaping outgoing traffic of network packets in a network management system
CN114342332A (zh) 一种通信方法、装置及系统
US8923120B2 (en) Adaptive queue-management
WO2019047939A1 (zh) 一种负载均衡方法、装置及业务编排器
RU2598293C1 (ru) Способ и устройство для передачи стандартных данных конфигурации усовершенствованной системы выбора протокола передачи
WO2016095142A1 (zh) 软件定义网络sdn中数据转发的方法、设备和系统
CN109962762A (zh) 一种数据传输方法、发送装置及接收装置
CN114466226A (zh) 带宽时长占比确定方法、装置、设备和计算机可读介质
KR20170101048A (ko) 네트워크에서 자원 예약의 해지 방법
CN109845217A (zh) 灵活以太网中传输数据的方法和设备
CN105009522B (zh) 一种部署增值业务的方法、网络设备及增值业务设备
Xu et al. A mathematical model and dynamic programming based scheme for service function chain placement in NFV
Reale et al. A bandwidth allocation model provisioning framework with autonomic characteristics
CN110830315B (zh) 一种网络功能构造方法及装置
KR101587379B1 (ko) 큐 사이즈의 동적 제어 방법 및 이를 수행하는 장치
US10945053B2 (en) Method and device for processing service crossing master node
WO2016095610A1 (zh) 一种恢复光层业务的方法和系统

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: 13868874

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 14762925

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2013868874

Country of ref document: EP