WO2015106729A1 - 一种负载均衡方法、装置和系统、计算机存储介质 - Google Patents

一种负载均衡方法、装置和系统、计算机存储介质 Download PDF

Info

Publication number
WO2015106729A1
WO2015106729A1 PCT/CN2015/071148 CN2015071148W WO2015106729A1 WO 2015106729 A1 WO2015106729 A1 WO 2015106729A1 CN 2015071148 W CN2015071148 W CN 2015071148W WO 2015106729 A1 WO2015106729 A1 WO 2015106729A1
Authority
WO
WIPO (PCT)
Prior art keywords
routing
controller
key value
group table
switch
Prior art date
Application number
PCT/CN2015/071148
Other languages
English (en)
French (fr)
Inventor
焦欣文
梁乾灯
陈然
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 EP15737198.0A priority Critical patent/EP3099032A4/en
Priority to US15/112,836 priority patent/US20160344633A1/en
Publication of WO2015106729A1 publication Critical patent/WO2015106729A1/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
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • 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
    • H04L41/0893—Assignment of logical groups to network elements
    • 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
    • H04L41/0895—Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
    • 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
    • H04L41/12—Discovery or management of network topologies
    • H04L41/122—Discovery or management of network topologies of virtualised topologies, e.g. software-defined networks [SDN] or network function virtualisation [NFV]
    • 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
    • H04L41/34—Signalling channels for network management communication
    • H04L41/342—Signalling channels for network management communication between virtual entities, e.g. orchestrators, SDN or NFV entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/24—Multipath
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/30—Routing of multiclass traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/50—Routing or path finding of packets in data switching networks using label swapping, e.g. multi-protocol label switch [MPLS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/40—Network security protocols
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L2101/00—Indexing scheme associated with group H04L61/00
    • H04L2101/60—Types of network addresses
    • H04L2101/618—Details of network addresses
    • H04L2101/622—Layer-2 addresses, e.g. medium access control [MAC] addresses
    • 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
    • H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
    • 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
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/508—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement
    • H04L41/5096—Network service management, e.g. ensuring proper service fulfilment according to agreements based on type of value added network service under agreement wherein the managed service relates to distributed or central networked applications
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/64—Routing or path finding of packets in data switching networks using an overlay routing layer

Definitions

  • the present invention relates to communication technologies, and in particular, to a load balancing method, apparatus and system, and computer storage medium.
  • SDN Software Defined Network
  • the OpenFlow protocol adopted by the SDN network separates the network device control plane (including the OpenFlow controller Controller) from the data plane (including the OpenFlow switch Capable Switch), thereby implementing flexible control of network traffic and providing innovation for core networks and applications.
  • the OpenFlow protocol adopted by the SDN network separates the network device control plane (including the OpenFlow controller Controller) from the data plane (including the OpenFlow switch Capable Switch), thereby implementing flexible control of network traffic and providing innovation for core networks and applications.
  • the OpenFlow protocol adopted by the SDN network separates the network device control plane (including the OpenFlow controller Controller) from the data plane (including the OpenFlow switch Capable Switch), thereby implementing flexible control of network traffic and providing innovation for core networks and applications.
  • the OpenFlow protocol adopted by the SDN network separates the network device control plane (including the OpenFlow controller Controller) from the data plane (including the OpenFlow switch Capable Switch), thereby implementing flexible control of network traffic and providing innovation for core networks and applications.
  • the OpenFlow protocol is used to describe the criteria used for the interaction between the controller and the switch, as well as the interface standards for the controller and switch.
  • the core part of the protocol is a collection of information structures for the OpenFlow protocol.
  • the controller manages the switch through the OpenFlow protocol. Through this protocol, the controller can incrementally or passively add, update, or delete flow entries.
  • Equal Cost Multi-Path is a technology that can effectively utilize the transmission bandwidth of the network.
  • traffic destined for a destination address can only use one of the links, other links are in backup or inactive state, and switching between links in a dynamic routing environment takes a certain amount of time.
  • traffic destined for a destination address can be allocated to multiple equal paths.
  • ECMP is implemented by a Select Group table: different ECMP forwarding paths are expressed by different buckets in the group table. After the packets enter the Openflow forwarding pipeline, they are executed. When a group table of the Select type of different buckets is included, the message is allocated to a certain bucket according to a certain load balancing algorithm.
  • a traffic identified by the controller is assigned to different paths by the switch's own routing algorithm, resulting in out-of-sequence;
  • the Openflow protocol defines multiple packet fields as the identifier of a traffic (the Openflow 1.3 version has 40 fields), while the traditional forwarding device often only selects a limited field to identify a flow, usually IP forwarding.
  • the source and destination MAC and label values are often forwarded by IP quintuple and Multi-Protocol Label Switching (MPLS).
  • MPLS Multi-Protocol Label Switching
  • the strength of the switch to identify traffic is often too coarse. When the strength of the switch identifies the traffic is too thick, the controller defines that the traffic cannot be refined. When the strength of the traffic identified by the controller is too thick, the traffic identified by the controller may be out of order.
  • embodiments of the present invention provide a load balancing method, apparatus, and system, and a computer storage medium.
  • the embodiment of the invention provides a load balancing method, and the method includes:
  • the switch sends a routing policy supported by the group table
  • the Select type group table When the Select type group table is executed on the traffic, the corresponding routing algorithm is executed according to the received routing policy.
  • the present invention provides another load balancing method, the method comprising:
  • the controller receives the routing strategy supported by the group table
  • a Select type group table entry and the specified routing policy are sent.
  • An embodiment of the present invention provides a load balancing method, where the method includes:
  • the switch sends a routing policy supported by the group table to the controller
  • the controller determines the designated routing policy according to the received routing policy and the service requirements of the application APP or the controller itself;
  • the controller sends a Select type group table entry and the specified routing policy to the switch;
  • the switch executes the Select type group table for the traffic, the switch performs the corresponding routing algorithm according to the specified routing policy.
  • An embodiment of the present invention provides a switch, where the switch includes:
  • a first sending unit configured to send a routing policy supported by the group table
  • a first receiving unit configured to receive a Select type group table entry and a specified routing policy
  • the execution unit is configured to execute a corresponding routing algorithm according to the received routing policy when the Select type group table is executed on the traffic.
  • An embodiment of the present invention provides a controller, where the controller includes:
  • a second receiving unit configured to receive a routing policy supported by the group table
  • a determining unit configured to determine a specified routing policy according to the received routing policy and the service requirement of the application APP or the controller itself;
  • a second sending unit configured to send a Select type group table entry and the specified routing policy.
  • An embodiment of the present invention provides a load balancing system, where the system includes a controller and at least one switch, wherein the switch is configured to send a routing policy supported by the group table to the controller; when the Select type group table is executed on the traffic When the corresponding routing algorithm is executed according to the specified routing strategy sent by the controller;
  • the controller is configured to determine a specified routing policy according to a routing policy sent by the switch, and a service requirement of the application APP or the controller itself; and send a Select type group table entry and the specified routing policy to the switch.
  • Embodiments of the present invention provide a computer storage medium in which computer executable instructions are stored, the computer executable instructions being used to perform the above method.
  • the technical solution of the embodiment of the present invention includes: the switch sends a routing policy supported by the group table; receives the Select type group table entry and the specified routing policy; when the Select type group table is executed on the traffic, according to the received designation
  • the routing strategy implements the corresponding routing algorithm. Therefore, the solution for the traffic ECMP load balancing in the SDN network provided by the embodiment of the present invention solves the problem that the packets of one stream are out of sequence.
  • 1 is a schematic structural diagram of an SDN network
  • FIG. 2 is a flowchart of an implementation of an embodiment of a load balancing method according to the present invention
  • FIG. 3 is a flowchart of an implementation of another method for load balancing according to the present invention.
  • FIG. 4 is a flowchart of an implementation of another embodiment of a load balancing method according to the present invention.
  • FIG. 5 is a schematic structural diagram of an embodiment of a switch provided by the present invention.
  • FIG. 6 is a schematic structural diagram of an embodiment of a controller provided by the present invention.
  • FIG. 7 is a schematic structural diagram of an embodiment of a load balancing system according to the present invention.
  • FIG. 8 is a flowchart of an implementation of a first embodiment of a load balancing method according to another embodiment of the present invention.
  • FIG. 9 is a flowchart of implementing a second embodiment of a load balancing method according to another embodiment of the present invention.
  • FIG. 10 is a flowchart of implementing a third embodiment of a load balancing method according to the present invention Figure.
  • FIG. 2 An embodiment of a load balancing method provided by the present invention is as shown in FIG. 2, where the method includes:
  • Step 201 The switch sends a routing policy supported by the group table.
  • the switch is an Openflow switch, and when the Openflow switch reports the group table capability to the controller, it informs the controller of the routing policy supported by the group table.
  • the routing policy includes at least one of a flow-by-flow and a packet-by-package, and the routing policy of the packet-by-packet mode is supported by default.
  • Step 202 Receive a Select type group table entry and specify a routing policy.
  • Step 203 When the Select type group table is executed on the traffic, the corresponding routing algorithm is executed according to the received routing policy.
  • the performing the routing algorithm according to the specified routing policy and the specified routing key value is:
  • the stream-by-flow algorithm is executed by extracting elements from the message according to the routing key value.
  • the method when the routing policy supported by the group table is flow-by-flow, the method further includes:
  • the switch sends a routing key value
  • the corresponding routing algorithm is executed according to the specified routing strategy and the specified routing key value.
  • the controller considers that the Openflow switch supports any combination of Match field fields as key values.
  • FIG. 3 Another embodiment of the load balancing method provided by the present invention is as shown in FIG. 3, and the method includes:
  • Step 301 The controller receives a routing policy supported by the group table.
  • Step 302 Determine a specified routing policy according to the received routing policy and the service requirement of the application APP or the controller itself.
  • Step 303 Send a Select type group table entry and the specified routing policy.
  • the method further includes:
  • the controller receives the routing key value
  • the specified routing key value is determined and sent according to the received routing key value and the application APP or the controller's own business requirements.
  • FIG. 4 Another load balancing method provided by the present invention is shown in FIG. 4, and the method includes:
  • Step 401 The switch sends a routing policy supported by the group table to the controller.
  • Step 402 The controller determines a specified routing policy according to the received routing policy and the service requirement of the application APP or the controller itself.
  • Step 403 The controller sends a Select type group table entry and the specified routing policy to the switch.
  • Step 404 When the switch executes the Select type group table for the traffic, the switch performs a corresponding routing algorithm according to the received routing policy.
  • the method when the routing policy supported by the group table is flow-by-flow, the method further includes:
  • the switch sends a routing key value to the controller
  • the controller determines the designated routing key value according to the received routing key value and the service requirement of the application APP or the controller itself, and sends the key value to the switch;
  • the switch performs the corresponding routing algorithm according to the specified routing policy and the specified routing key value.
  • the switch includes:
  • the first sending unit 501 is configured to send a routing policy supported by the group table
  • the first receiving unit 502 is configured to receive a Select type group table entry and specify a routing policy
  • the executing unit 503 is configured to execute a corresponding routing algorithm according to the received specified routing policy when the Select type group table is executed on the traffic.
  • the first sending unit 501 is further configured to send a routing key value
  • the first receiving unit 502 is further configured to receive the designated routing key value
  • the executing unit 503 is configured to execute a corresponding routing algorithm according to the received routing policy and the specified routing key value when the Select type group table is executed on the traffic.
  • the execution unit 503 may be specifically configured to extract an element from the message according to the routing key value, and perform a flow-by-flow algorithm.
  • the controller includes:
  • the second receiving unit 601 is configured to receive a routing policy supported by the group table
  • the determining unit 602 is configured to determine a specified routing policy according to the received routing policy and the service requirement of the application APP or the controller itself;
  • the second sending unit 603 is configured to send a Select type group table entry and the specified routing policy.
  • the second receiving unit 601 is further configured to receive a routing key value
  • the determining unit 602 is further configured to determine, according to the received routing key value, and the service requirement of the application APP or the controller itself, the specified routing key value;
  • the second sending unit 603 is further configured to send the specified routing key value.
  • the system includes a controller and at least one switch, wherein the switch 701 is configured to send a routing policy supported by the group table to the controller.
  • the switch 701 is configured to send a routing policy supported by the group table to the controller.
  • the Select type group table is executed on the traffic, the corresponding routing algorithm is executed according to the specified routing policy sent by the controller;
  • the controller 702 is configured to determine a specified routing policy according to a routing policy sent by the switch, and a service requirement of the application APP or the controller itself; and send a Select type group table entry and the specified routing policy to the switch.
  • the switch 701 when the routing policy supported by the group table is flow-by-flow, the switch 701 is configured to send a routing key value to the controller; according to the specified routing policy and the specified routing sent by the controller.
  • the key value performs a corresponding routing algorithm
  • the controller 702 is further configured to determine the designated routing key value according to the received routing key value and the service requirement of the application APP or the controller itself, and send the value to the switch.
  • a first embodiment of a load balancing method provided by the present invention includes the following steps:
  • Step 801 When the Openflow switch reports the capability of the group table to the controller, the controller is notified of the routing policy supported by the group table.
  • the data packets to the same destination are balancedly allocated to different paths.
  • the packets destined to the same destination address are based on the routing key value. Divide into different streams and then assign different streams to different paths.
  • the controller considers that the Openflow switch supports all Match fields as key values.
  • step 802 when the controller sends a Select type group table entry to the switch according to the application (APP) or the service requirement of the controller, the controller also delivers the selected one routing policy, and the selected one routing policy is called designation. Routing strategy.
  • the selected routing strategy is within the capabilities reported by the Openflow switch.
  • the controller When the controller sends a Select type group table entry to the switch according to the APP or its own service requirement, when the selected routing policy is a flow-by-flow routing policy, the controller further needs to issue the routing key value. .
  • step 803 when the traffic is executed in the Openflow switch in the Select type group table, different routing algorithms are executed according to the routing policy in the group table.
  • routing strategy selected in step 802 is a flow-by-flow routing strategy
  • this step when When the traffic is executed in the OpenFlow switch in the Select type group table, in addition to selecting the routing algorithm according to the routing policy in the group table, it is further necessary to perform the routing algorithm according to the routing key value.
  • the routing policy of the ECMP load balancing of the SDN network is packet-by-package. As shown in FIG. 9, the embodiment includes the following steps:
  • Step 901 When the Openflow switch reports the group table capability to the controller, the controller is notified of the routing policy supported by the group table (including at least a packet-by-packet).
  • the Openflow switch when the Openflow switch reports the group table capability to the controller through the OFMPMP_GROUP_FEATURES reply message defined by the Openflow protocol, it can only report whether the flow-by-flow routing policy is supported. By default, the packet-by-packet routing policy is supported.
  • step 902 when the controller sends a Select type group table entry to the switch through the OFPT_GROUP_MOD message according to the APP or its own service requirement, the controller also delivers the selected one routing policy.
  • the routing policy selected by the controller according to the APP or its own business requirements is a packet-by-package routing strategy.
  • Step 903 When the traffic is executed in the Openflow switch in the Select type group table, the routing algorithm is executed according to the routing policy in the group table.
  • OFPT_GROUP_MOD Extend the OFPT_GROUP_MOD message to increase the routing strategy (packet-by-packet or flow-by-flow) and routing key values.
  • the latter is a variable-length array that only takes effect on the Select type and the routing policy is a flow-by-flow group table entry.
  • the Openflow switch receives the Select-type group table entry, if it does not support flow-by-flow, or the parameters do not correspond, or there are unsupported routing key values, the error message is returned, and the corresponding error type and error code information are carried to the control. Device.
  • the data structure of the routing key value in the above extension may borrow the definition of struct ofp_table_feature_prop_oxm, which is a variable length data definition type.
  • a third embodiment of a load balancing method provided by the present invention the SDN network in this embodiment
  • the routing strategy for network ECMP load balancing is flow-by-flow. As shown in FIG. 10, the embodiment includes the following steps:
  • step 1001 when the Openflow switch reports the group table capability to the controller, it notifies the controller of the routing policy supported by the group table (including at least flow-by-flow).
  • the Openflow switch when the Openflow switch reports the group table capability to the controller, it can report only the routing policy supporting the flow-by-flow and the supported routing key value.
  • the routing key value can be reused in the Match field.
  • the tuple (source IP, destination IP, protocol type, source port, destination port) is used as the key value routing, and also supports any Match preset field set as the key value routing.
  • step 1002 when the controller sends a Select type group table entry to the switch according to the service requirement of the APP or the service, the controller also issues a selected routing policy and a routing key (for example, a quintuple).
  • a routing key for example, a quintuple
  • the routing strategy selected by the controller according to the APP or its own business requirements is a flow-by-flow routing strategy.
  • Step 1003 When the traffic is executed in the Openflow switch in the Select type group table, the routing algorithm is executed according to the routing policy and the routing key value in the group table.
  • the Openflow switch extracts elements from the packet according to the routing key value sent by the controller, and then performs a flow-by-flow algorithm, and the routing algorithm can be independently selected by the Openflow switch, as long as the hash is effectively hashed according to the routing key value. can.
  • the embodiment of the present invention further provides a computer storage medium, wherein computer executable instructions are stored, the computer executable instructions being used to execute the method described in any one of the foregoing method embodiments.
  • the solution of the traffic ECMP load balancing in the SDN network provided by the embodiment of the present invention can finely control the traffic and solve the problem of packet out of sequence of one stream.
  • Each of the above units may be implemented by a central processing unit (CPU), a digital signal processor (DSP), or a field-programmable gate array (FPGA) in an electronic device.
  • CPU central processing unit
  • DSP digital signal processor
  • FPGA field-programmable gate array
  • embodiments of the present invention can be provided as a method, system, Or a computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Abstract

本发明公开了一种负载均衡方法、装置和系统、计算机存储介质，其中，一种负载均衡方法包括：交换机向控制器发送组表支持的选路策略；控制器根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；控制器向交换机发送Select类型组表条目和所述指定选路策略；交换机当对流量执行Select类型组表时，根据收到的所述指定选路策略执行相应的选路算法。

Description

一种负载均衡方法、装置和系统、计算机存储介质 技术领域
本发明涉及通信技术，尤其涉及一种负载均衡方法、装置和系统、计算机存储介质。
背景技术
软件定义网络(Software Defined Network，SDN)是一种新型网络创新架构。SDN网络采用的OpenFlow协议通过将网络设备控制面(包含OpenFlow控制器Controller)与数据面(包含OpenFlow交换机Capable Switch)分离开来，从而实现了网络流量的灵活控制，为核心网络及应用的创新提供了良好的平台。
OpenFlow协议用来描述控制器和交换机之间交互所用信息的标准，以及控制器和交换机的接口标准。协议的核心部分是用于OpenFlow协议信息结构的集合。
控制器通过OpenFlow协议来管理交换机。通过此协议，控制器既可以主动也可被动的增加、更新或删除流表项(flow entry)。
等价多路径(Equal Cost Multi-Path，ECMP)是一种能够有效利用网络传输带宽的技术。在传统路由技术中，发往某一目的地址的流量只能利用其中的一条链路，其他链路处于备份或者无效状态，并且在动态路由环境下链路之间的切换需要一定的时间。而在引入ECMP技术下，发往某一目的地址的流量能够被分配到多个等价的路径上。
在实际转发中，设备往往通过不同的策略实现流量在不同路径上负载均衡(Load Balancing)，进一步的提升流量转发中的链路利用效率。常见的分流策略有：逐包(per packet)和逐流(per flow)。在逐包策略负载均衡 下，到同一个目的的数据报文，被均衡的分配到不同的路径上；而在逐流策略负载均衡下，到同一个目的地址的报文，依据报文中一些元素(IP报文往往是五元组：源IP地址、目的IP地址、IP协议号、源端口号、目的端口号)划分为不同流(Flow)，然后将不同流均衡的分配到不同的路径上。
根据现有Openflow协议，ECMP是通过Select类型的组表(Group Table)来实现的：不同的ECMP转发路径通过组表下不同的容器(bucket)来表达，当报文进入Openflow转发管道后执行到包含不同的bucket的Select类型的组表时，将根据一定负载均衡算法把报文分配到某一个bucket中处理。
但是，现有Openflow协议中，在执行Select类型的组表的时候，Openflow控制器并没有指定交换机采用什么负载均衡算法，也没有指明参与负荷分担计算的报文元素。因此就存在下面两点问题：
在逐包策略下，控制器认定的一条流量被交换机自己的选路算法分配到了不同路径上，导致失序；
在逐流策略下，Openflow协议定义了多个报文字段作为一条流量的标识(Openflow1.3版本有40个字段)，而传统转发设备往往只会选取有限的字段来标识一条流，通常IP转发往往以IP五元组，多协议标签交换(Multi-Protocol Label Switching，MPLS)转发以源、目的MAC和标签值，交换机标识流量的力度往往过粗。当交换机标识流量的力度过粗时，控制器定义流量得不到精细化的控制；而当控制器标识的流量的力度过粗时，控制器认定的流量就有可能失序。
发明内容
为解决现有存在的技术问题，本发明实施例提供一种负载均衡方法、装置和系统、计算机存储介质，具体的：
本发明实施例提供一种负载均衡方法，所述方法包括：
交换机发送组表支持的选路策略；
接收Select类型组表条目和指定选路策略；
当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
本发明提供另一种负载均衡方法，所述方法包括：
控制器接收组表支持的选路策略；
根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
发送Select类型组表条目和所述指定选路策略。
本发明实施例提供再一种负载均衡方法，所述方法包括：
交换机向控制器发送组表支持的选路策略；
控制器根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
控制器向交换机发送Select类型组表条目和所述指定选路策略；
交换机当对流量执行Select类型组表时，根据收到的所述指定选路策略执行相应的选路算法。
本发明实施例提供一种交换机，所述交换机包括：
第一发送单元，配置为发送组表支持的选路策略；
第一接收单元，配置为接收Select类型组表条目和指定选路策略；
执行单元，配置为当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
本发明实施例提供一种控制器，所述控制器包括：
第二接收单元，配置为接收组表支持的选路策略；
确定单元，配置为根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
第二发送单元，配置为发送Select类型组表条目和所述指定选路策略。
本发明实施例提供一种负载均衡系统，所述系统包括控制器和至少一个交换机，其中，所述交换机，配置为向控制器发送组表支持的选路策略；当对流量执行Select类型组表时，根据控制器发来的指定选路策略执行相应的选路算法；
所述控制器，配置为根据交换机发来的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；向交换机发送Select类型组表条目和所述指定选路策略。
本发明实施例提供一种计算机存储介质，其中存储有计算机可执行指令，所述计算机可执行指令用于执行上述的方法。
由上可知，本发明实施例的技术方案包括：交换机发送组表支持的选路策略；接收Select类型组表条目和指定选路策略；当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。由此，本发明实施例提供的SDN网络中流量ECMP负载均衡的解决方案，解决一条流的报文失序的问题。
附图说明
图1为SDN网络的结构示意图；
图2为本发明提供的一种负载均衡方法的实施例的实现流程图；
图3为本发明提供的另一种负载均衡方法的实施例的实现流程图；
图4为本发明提供的再一种负载均衡方法的实施例的实现流程图；
图5为本发明提供的交换机的实施例的结构示意图；
图6为本发明提供的控制器的实施例的结构示意图；
图7为本发明提供的负载均衡系统的实施例的结构示意图；
图8为本发明提供的再一种负载均衡方法的第一实施例的实现流程图；
图9为本发明提供的再一种负载均衡方法的第二实施例的实现流程图；
图10为本发明提供的再一种负载均衡方法的第三实施例的实现流程 图。
具体实施方式
本发明提供的一种负载均衡方法的实施例，如图2所示，所述方法包括：
步骤201、交换机发送组表支持的选路策略；
这里，所述交换机为Openflow交换机，Openflow交换机向控制器上报组表能力时，告知控制器该组表所支持的选路策略。所述选路策略至少包括逐流和逐包中的一种，默认支持逐包模式的选路策略。
步骤202、接收Select类型组表条目和指定选路策略；
步骤203、当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
这里，所述根据指定选路策略和指定选路键值执行相应的选路算法为：
根据选路键值从报文中提取元素，执行逐流算法。
在一实施例中，当组表支持的选路策略为逐流时，所述方法还包括：
交换机发送选路键值；
接收指定选路键值；
相应的，所述执行相应的选路算法为：
根据收到的指定选路策略和指定选路键值执行相应的选路算法。
这里，默认情况下控制器认为Openflow交换机支持任意的匹配域(Match field)字段组合作为键值。
本发明提供的另一种负载均衡方法的实施例，如图3所示，所述方法包括：
步骤301、控制器接收组表支持的选路策略；
步骤302、根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
步骤303、发送Select类型组表条目和所述指定选路策略。
在一实施例中，所述方法还包括：
控制器接收选路键值；
根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送。
本发明提供的再一种负载均衡方法，如图4所示，所述方法包括：
步骤401、交换机向控制器发送组表支持的选路策略；
步骤402、控制器根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
步骤403、控制器向交换机发送Select类型组表条目和所述指定选路策略；
步骤404、交换机当对流量执行Select类型组表时，根据收到的所述指定选路策略执行相应的选路算法。
在一实施例中，当组表支持的选路策略为逐流时，所述方法还包括：
交换机向控制器发送选路键值；
控制器根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送给交换机；
相应的，所述执行相应的选路算法为：
交换机根据收到的指定选路策略和指定选路键值执行相应的选路算法。
本发明提供的一种交换机的实施例，如图5所示，所述交换机包括：
第一发送单元501，配置为发送组表支持的选路策略；
第一接收单元502，配置为接收Select类型组表条目和指定选路策略；
执行单元503，配置为当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
在一实施例中，所述第一发送单元501，还配置为发送选路键值；
第一接收单元502，还配置为接收指定选路键值；
执行单元503，具体配置为当对流量执行Select类型组表时，根据收到的指定选路策略和指定选路键值执行相应的选路算法。
这里，执行单元503可以具体配置为根据选路键值从报文中提取元素，执行逐流算法。
本发明提供的一种控制器的实施例，如图6所示，所述控制器包括：
第二接收单元601，配置为接收组表支持的选路策略；
确定单元602，配置为根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
第二发送单元603，配置为发送Select类型组表条目和所述指定选路策略。
在一实施例中，所述第二接收单元601，还配置为接收选路键值；
确定单元602，还配置为根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值；
第二发送单元603，还配置为发送所述指定选路键值。
本发明提供的一种负载均衡系统的实施例，如图7所示，所述系统包括控制器和至少一个交换机，其中，所述交换机701，配置为向控制器发送组表支持的选路策略；当对流量执行Select类型组表时，根据控制器发来的指定选路策略执行相应的选路算法；
所述控制器702，配置为根据交换机发来的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；向交换机发送Select类型组表条目和所述指定选路策略。
在一实施例中，当组表支持的选路策略为逐流时，所述交换机701，配置为向控制器发送选路键值；根据控制器发来的指定选路策略和指定选路 键值执行相应的选路算法；
所述控制器702，还配置为根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送给交换机。
本发明提供的再一种负载均衡方法的第一实施例，如图8所示，本实施例包括以下步骤：
步骤801，Openflow交换机向控制器上报组表的能力时，告知控制器所述组表所支持的选路策略。
此步骤中，选路策略有两种，即逐包(per packet)和逐流(per flow)。
在逐包策略负载均衡下，到同一个目的的数据报文，被均衡的分配到不同的路径上；而在逐流策略负载均衡下，到同一个目的地址的报文，依据选路键值划分为不同流(Flow)，然后将不同流均衡的分配到不同的路径上。
默认情况下控制器认为Openflow交换机支持所有的Match域作为键值。
步骤802，控制器根据应用(APP)或者控制器自身的业务需求向交换机下发Select类型组表条目时，还下发所选择的一种选路策略，选择的一种选路策略称为指定选路策略。
在此步骤中，所选的一种选路策略是在Openflow交换机所上报的能力范围内。
控制器根据APP或者自身的业务需求向交换机下发Select类型组表条目时，还下发所选择的一种选路策略是逐流的选路策略时，进一步的还需要下发选路键值。
步骤803，当流量在Openflow交换机中进行Select类型的组表执行时，根据组表中的选路策略，执行不同的选路算法。
当步骤802所选的一种选路策略是逐流的选路策略时，本步骤中，当 流量在Openflow交换机中进行Select类型的组表执行时，除了根据组表中的选路策略来选择选路算法外，进一步的还需要根据选路键值来进行选路算法。
本发明提供的再一种负载均衡方法的第二实施例，本实施例中SDN网络ECMP负载均衡的选路策略是逐包，如图9所示，本实施例包括以下步骤：
步骤901，Openflow交换机向控制器上报组表能力时，告知控制器该组表所支持的选路策略(至少包含逐包)。
此步骤中，Openflow交换机通过Openflow协议定义的OFPMP_GROUP_FEATURES reply消息向控制器上报组表能力时，可以只上报是否支持逐流的选路策略，默认支持逐包选路策略。
步骤902，控制器根据APP或者自身的业务需求向交换机通过OFPT_GROUP_MOD消息下发Select类型组表条目时，还下发所选择的一种选路策略。
在此步骤中，控制器根据APP或者自身的业务需求所选的选路策略是逐包的选路策略。
步骤903，当流量在Openflow交换机中进行Select类型的组表执行时，根据组表中的选路策略，执行选路算法。
数据结构描述如下：
(1)扩展OFPMP_GROUP_FEATURES reply消息中的capabilities中标记位，用于表示组表支持的选路策略：
Figure PCTCN2015071148-appb-000001
Figure PCTCN2015071148-appb-000002
(2)扩展OFPT_GROUP_MOD消息,增加选路策略(逐包或逐流)和选路键值。后者是变长数组，仅在Select类型且选路策略为逐流的组表条目上生效。Openflow交换机收到这种Select类型的组表条目时，如果不支持逐流，或者参数不对应，或者有不支持的选路键值，回复Error消息，携带对应的错误类型和错误码信息给控制器。
上述扩展中的选路键值的数据结构可以借用struct ofp_table_feature_prop_oxm的定义，该数据结构为变长数据定义类型。
Figure PCTCN2015071148-appb-000003
Figure PCTCN2015071148-appb-000004
Figure PCTCN2015071148-appb-000005
本发明提供的再一种负载均衡方法的第三实施例，本实施例中SDN网 络ECMP负载均衡的选路策略是逐流。如图10所示，本实施例包括以下步骤：
步骤1001，Openflow交换机向控制器上报组表能力时，告知控制器该组表所支持的选路策略(至少包含逐流)。
此步骤中，Openflow交换机向控制器上报组表能力时，可以只上报支持逐流的选路策略和所支持选路键值，该选路键值可以复用Match域已有定义，支持根据五元组(源IP、目的IP、协议类型、源端口、目的端口)作为键值选路，也支持任意Match预置定义字段集合作为键值的选路。
步骤1002，控制器根据APP或者自身的业务需求向交换机下发Select类型组表条目时，还下发所选择的一种选路策略及选路键值(例如五元组)。
在此步骤中，控制器根据APP或者自身的业务需求所选的选路策略是逐流的选路策略。
步骤1003，当流量在Openflow交换机中进行Select类型的组表执行时，根据组表中的选路策略及选路键值，执行选路算法。
此步骤中，Openflow交换机则根据控制器下发的选路键值从报文中提取元素，然后执行逐流算法，选路算法可以由Openflow交换机自主选择，只要根据选路键值有效散列即可。
本发明实施例还提供一种计算机存储介质，其中存储有计算机可执行指令，所述计算机可执行指令用于执行上述任一方法实施例所述的方法。
综上所述，本发明实施例提供的SDN网络中流量ECMP负载均衡的解决方案，能够对流量进行精细化控制，并且解决一条流的报文失序的问题。
上述各单元可以由电子设备中的中央处理器(Central Processing Unit，CPU)、数字信号处理器(Digital Signal Processor，DSP)或可编程逻辑阵列(Field－Programmable Gate Array，FPGA)实现。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、 或计算机程序产品。因此，本发明可采用硬件实施例、软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器和光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。

Claims (15)

  1. 一种负载均衡方法，其中，所述方法包括：
    交换机发送组表支持的选路策略；
    接收Select类型组表条目和指定选路策略；
    当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
  2. 根据权利要求1所述的方法，其中，当组表支持的选路策略为逐流时，所述方法还包括：
    交换机发送选路键值；
    接收指定选路键值；
    相应的，所述执行相应的选路算法为：
    根据收到的指定选路策略和指定选路键值执行相应的选路算法。
  3. 根据权利要求2所述的方法，其中，所述根据指定选路策略和指定选路键值执行相应的选路算法为：
    根据选路键值从报文中提取元素，执行逐流算法。
  4. 一种负载均衡方法，其中，所述方法包括：
    控制器接收组表支持的选路策略；
    根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
    发送Select类型组表条目和所述指定选路策略。
  5. 根据权利要求4所述的方法，其中，所述方法还包括：
    控制器接收选路键值；
    根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送。
  6. 一种负载均衡方法，其中，所述方法包括：
    交换机向控制器发送组表支持的选路策略；
    控制器根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
    控制器向交换机发送Select类型组表条目和所述指定选路策略；
    交换机当对流量执行Select类型组表时，根据收到的所述指定选路策略执行相应的选路算法。
  7. 根据权利要求6所述的方法，其中，当组表支持的选路策略为逐流时，所述方法还包括：
    交换机向控制器发送选路键值；
    控制器根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送给交换机；
    相应的，所述执行相应的选路算法为：
    交换机根据收到的指定选路策略和指定选路键值执行相应的选路算法。
  8. 一种交换机，其中，所述交换机包括：
    第一发送单元，配置为发送组表支持的选路策略；
    第一接收单元，配置为接收Select类型组表条目和指定选路策略；
    执行单元，配置为当对流量执行Select类型组表时，根据收到的指定选路策略执行相应的选路算法。
  9. 根据权利要求8所述的交换机，其中，所述第一发送单元，还配置为发送选路键值；
    第一接收单元，还配置为接收指定选路键值；
    执行单元，具体配置为当对流量执行Select类型组表时，根据收到的指定选路策略和指定选路键值执行相应的选路算法。
  10. 根据权利要求9所述的交换机，其中，执行单元，具体配置为根据选路键值从报文中提取元素，执行逐流算法。
  11. 一种控制器，其中，所述控制器包括：
    第二接收单元，配置为接收组表支持的选路策略；
    确定单元，配置为根据接收到的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；
    第二发送单元，配置为发送Select类型组表条目和所述指定选路策略。
  12. 根据权利要求11所述的控制器，其中，所述第二接收单元，还配置为接收选路键值；
    确定单元，还配置为根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值；
    第二发送单元，还配置为发送所述指定选路键值。
  13. 一种负载均衡系统，其中，所述系统包括控制器和至少一个交换机，其中，所述交换机，配置为向控制器发送组表支持的选路策略；当对流量执行Select类型组表时，根据控制器发来的指定选路策略执行相应的选路算法；
    所述控制器，配置为根据交换机发来的选路策略，以及应用APP或者控制器自身的业务需求确定指定选路策略；向交换机发送Select类型组表条目和所述指定选路策略。
  14. 根据权利要求13所述的系统，其中，当组表支持的选路策略为逐流时，所述交换机，配置为向控制器发送选路键值；根据控制器发来的指定选路策略和指定选路键值执行相应的选路算法；
    所述控制器，还配置为根据接收到的选路键值，以及应用APP或者控制器自身的业务需求确定指定选路键值并发送给交换机。
  15. 一种计算机存储介质，其中存储有计算机可执行指令，所述计算机可执行指令用于执行所述权利要求1至3、权利要求4至5、权利要求6至7任一项所述的方法。
PCT/CN2015/071148 2014-01-20 2015-01-20 一种负载均衡方法、装置和系统、计算机存储介质 WO2015106729A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP15737198.0A EP3099032A4 (en) 2014-01-20 2015-01-20 A load balancing method, device, system and computer storage medium
US15/112,836 US20160344633A1 (en) 2014-01-20 2015-01-20 Load balancing method, device, system and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410026424.5A CN104796347A (zh) 2014-01-20 2014-01-20 一种负载均衡方法、装置和系统
CN201410026424.5 2014-01-20

Publications (1)

Publication Number Publication Date
WO2015106729A1 true WO2015106729A1 (zh) 2015-07-23

Family

ID=53542432

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/071148 WO2015106729A1 (zh) 2014-01-20 2015-01-20 一种负载均衡方法、装置和系统、计算机存储介质

Country Status (4)

Country Link
US (1) US20160344633A1 (zh)
EP (1) EP3099032A4 (zh)
CN (1) CN104796347A (zh)
WO (1) WO2015106729A1 (zh)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10110684B1 (en) 2013-08-15 2018-10-23 Avi Networks Transparent network service migration across service devices
US9843520B1 (en) * 2013-08-15 2017-12-12 Avi Networks Transparent network-services elastic scale-out
CN104980361B (zh) * 2014-04-01 2018-09-21 华为技术有限公司 一种负载均衡方法、装置及系统
US10404577B2 (en) * 2014-08-28 2019-09-03 Hewlett Packard Enterprise Development Lp Network compatibility determination based on flow requirements of an application and stored flow capabilities of a software-defined network
US11283697B1 (en) 2015-03-24 2022-03-22 Vmware, Inc. Scalable real time metrics management
WO2017000243A1 (zh) * 2015-06-30 2017-01-05 华为技术有限公司 一种路由的方法、相关设备及系统
CN106330783B (zh) * 2015-07-01 2019-03-15 中兴通讯股份有限公司 一种OpenFlow交换机能力上报的方法及装置
US10498654B2 (en) * 2015-12-28 2019-12-03 Amazon Technologies, Inc. Multi-path transport design
US9985904B2 (en) 2015-12-29 2018-05-29 Amazon Technolgies, Inc. Reliable, out-of-order transmission of packets
CN107995123B (zh) * 2016-10-27 2020-05-01 贵州白山云科技股份有限公司 一种基于交换机的负载均衡系统及方法
CN117478580A (zh) * 2022-07-29 2024-01-30 华为技术有限公司 一种发送负载信息的方法、发送报文的方法及装置
CN117240787B (zh) * 2023-11-14 2024-03-01 鹏城实验室 交换机负载均衡方法、装置、电子设备及可读存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101360050A (zh) * 2008-09-25 2009-02-04 福建星网锐捷网络有限公司 一种设置流控模式的方法及装置
US20130223226A1 (en) * 2012-02-29 2013-08-29 Dell Products, Lp System and Method for Providing a Split Data Plane in a Flow-Based Switching Device
US20130272135A1 (en) * 2012-04-11 2013-10-17 Gigamon Llc Traffic visibility in an open networking environment

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10103939B2 (en) * 2010-07-06 2018-10-16 Nicira, Inc. Network control apparatus and method for populating logical datapath sets
CN103067534B (zh) * 2012-12-26 2016-09-28 中兴通讯股份有限公司 一种NAT实现系统、方法及Openflow交换机
CN103200122B (zh) * 2013-03-05 2016-08-10 国家电网公司 一种软件定义网络中组表的处理方法、系统和控制器

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101360050A (zh) * 2008-09-25 2009-02-04 福建星网锐捷网络有限公司 一种设置流控模式的方法及装置
US20130223226A1 (en) * 2012-02-29 2013-08-29 Dell Products, Lp System and Method for Providing a Split Data Plane in a Flow-Based Switching Device
US20130272135A1 (en) * 2012-04-11 2013-10-17 Gigamon Llc Traffic visibility in an open networking environment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
OPEN NETWORKING FOUNDATION, OPENFLOW SWITCH SPECIFICATION, vol. 1.3.2, 25 April 2013 (2013-04-25), XP055213379 *
See also references of EP3099032A4 *

Also Published As

Publication number Publication date
US20160344633A1 (en) 2016-11-24
CN104796347A (zh) 2015-07-22
EP3099032A4 (en) 2017-01-11
EP3099032A1 (en) 2016-11-30

Similar Documents

Publication Publication Date Title
WO2015106729A1 (zh) 一种负载均衡方法、装置和系统、计算机存储介质
US9674088B1 (en) Receive packet steering for virtual networks
US10742722B2 (en) Server load balancing
US9667538B2 (en) Method and apparatus for connecting a gateway router to a set of scalable virtual IP network appliances in overlay networks
EP3082309B1 (en) Sdn controller, data centre system and router connection method
KR102205882B1 (ko) 팻-트리 라우팅에 기반하여 별개의 인피니밴드 서브넷들 사이에서 트래픽을 라우팅하기 위한 시스템 및 방법
EP3399703B1 (en) Method for implementing load balancing, apparatus, and network system
WO2016098031A1 (en) Method and system for load balancing in a software-defined networking (sdn) system upon server reconfiguration
WO2015109821A1 (zh) 一种管理业务链的方法、系统及装置
US9397926B2 (en) Peer-influenced aggregate member selection
WO2021000848A1 (zh) 一种报文转发方法、报文处理方法及装置
WO2015170204A1 (en) Implementing a 3g packet core in a cloud computer with openflow data and control planes
EP3541028B1 (en) Adaptive load-balancing over a multi-point logical interface
EP2676410A1 (en) Flow communication system
CN108476175B (zh) 使用对偶变量的传送sdn流量工程方法与系统
Trivisonno et al. Virtual links mapping in future sdn-enabled networks
US9800508B2 (en) System and method of flow shaping to reduce impact of incast communications
JPWO2014112616A1 (ja) 制御装置、通信装置、通信システム、スイッチの制御方法及びプログラム
WO2018219103A1 (zh) 一种链路状态确定方法及设备
CN105745874A (zh) 一种确定服务功能路径的方法及装置
EP3241309A1 (en) Overprovisioning floating ip addresses to provide stateful ecmp for traffic groups
WO2015135284A1 (zh) 数据流转发的控制方法及系统、计算机存储介质
WO2015162619A1 (en) Managing link failures in software defined networks
US10177935B2 (en) Data transfer system, data transfer server, data transfer method, and program recording medium
Chang et al. Using sdn technology to mitigate congestion in the openstack data center network

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: 15737198

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: 15112836

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2015737198

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2015737198

Country of ref document: EP