WO2023279555A1 - 一种拓扑感知的负载均衡方法、装置及计算机设备 - Google Patents

一种拓扑感知的负载均衡方法、装置及计算机设备 Download PDF

Info

Publication number
WO2023279555A1
WO2023279555A1 PCT/CN2021/121912 CN2021121912W WO2023279555A1 WO 2023279555 A1 WO2023279555 A1 WO 2023279555A1 CN 2021121912 W CN2021121912 W CN 2021121912W WO 2023279555 A1 WO2023279555 A1 WO 2023279555A1
Authority
WO
WIPO (PCT)
Prior art keywords
topology
link
load balancing
information
service endpoints
Prior art date
Application number
PCT/CN2021/121912
Other languages
English (en)
French (fr)
Inventor
李丰启
Original Assignee
苏州浪潮智能科技有限公司
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 苏州浪潮智能科技有限公司 filed Critical 苏州浪潮智能科技有限公司
Priority to US18/271,456 priority Critical patent/US11902362B2/en
Publication of WO2023279555A1 publication Critical patent/WO2023279555A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
    • 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
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/101—Server selection for load balancing based on network conditions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0811—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity

Definitions

  • the present application relates to the technical field of load balancing, and in particular to a topology-aware load balancing method, device and equipment.
  • the traditional load balancing strategy cannot perceive the topology information of the load balancing backend service endpoints, leading to two problems: First, the load balancing system cannot effectively and reasonably plan the backend service endpoint resources, resulting in the backend that provides services for the load balancing frontend The service endpoint is not optimal, the user experience is poor, and the data center resources cannot be used reasonably; secondly, users can plan the topology of the load balancing backend service endpoint reasonably to achieve the optimal system, but when the load balancing backend service endpoint topology Due to changes caused by faults, insufficient computing resources, etc., the system cannot automatically adjust the load balancing rules, but requires operation and maintenance personnel to manually readjust according to the new topology, resulting in high risk of error and high operation and maintenance costs.
  • the purpose of the embodiment of the present application is to propose a topology-aware load balancing method, device, and computer equipment, using topology-aware and link-quality-aware methods to calculate the priority of the load-balancing backend service endpoint according to the priority algorithm , select the optimal backend service endpoint as the backend of the load balancing service, and at the same time, when the network status changes or the topology of the backend service endpoint changes, the load balancing can automatically adapt to the latest topology and link status, without upgrading the hardware It makes full use of the link bandwidth resources of the data center network to bring users the best experience.
  • an aspect of the embodiment of the present application provides a topology-aware load balancing method, including the following steps: obtaining the load balancing configuration information sent by the user, and judging whether several backend service endpoints of the load balancing are based on the configuration information Located on different nodes; if several back-end service endpoints of load balancing are located on different nodes, the commands to poll several back-end service endpoints on their respective nodes are regularly sent to different nodes to obtain the topology information of different nodes, several back-end service endpoints health status and link quality; based on topology information, health status and link quality, calculate the priority of several back-end service endpoints, and set the service response endpoint for balanced load based on priority; and respond to changes in topology information and /or the health status and/or link quality change, recalculate the priority of several backend service endpoints, and adjust the service response endpoint based on the priority.
  • it also includes: the topology awareness modules of different nodes perform regular polling on several back-end service endpoints on respective nodes, to obtain topology information of different nodes, and upload the topology information to the control module;
  • the health monitoring module polls several back-end service endpoints on respective nodes periodically to obtain the health status and link information of several back-end service endpoints, and uploads the health status and link information to the control module.
  • responding to changes in topology information and/or changes in health status and/or link quality includes: obtaining current topology information by a topology perception module, and judging whether the current topology information is the same as the topology information obtained last time ; If the current topology information is different from the topology information obtained last time, confirm that the topology information has changed, and upload the current topology information to the control module; the health monitoring module obtains the current health status and current link information, and updates the current health status and The current link information is uploaded to the control module, and the control module judges whether the health status and link quality have changed based on the current health status and current link information and the health status and link information acquired last time.
  • the method further includes: if the current topology information is the same as the topology information obtained last time, and confirming that the topology information has not changed, then the current topology information will not be uploaded to the control module.
  • calculating the priority of several backend service endpoints based on topology information, health status and link quality includes: calculating the average link cost based on the link cost in the link quality, and calculating the average link cost based on the link average Cost, topology weight, link weight, link overhead weight, link stability weight, and delay change weight are calculated to obtain the load balancing priority of several backend service endpoints.
  • calculating the load balancing priorities of several backend service endpoints based on link average cost, topology weight, link weight, link cost weight, link stability weight, and delay change weight includes: through the following formula Calculate the priority of several backend service endpoints:
  • a 1 is the topology weight of topology T
  • a 2 is the link weight
  • x 1 , x 2 ,..., x n is the link cost of the corresponding link
  • a 3 is the link cost weight
  • a 4 is the link weight
  • L is the delay change weight
  • M is the average cost of the link.
  • setting the load balancing service response endpoint based on priority includes: sorting the priorities of several backend service endpoints from high to low, and using the backend service endpoint with the highest priority as the load balancing service response endpoint.
  • adjusting the service response endpoint based on the priority includes: sorting the priorities obtained by recalculating several backend service endpoints from high to low, and using the recalculated priority of the highest priority backend service endpoint as the load Balanced service response endpoint.
  • a topology-aware load balancing device including: a first module configured to obtain load balancing configuration information issued by users, and determine several post-load balancing tasks based on the configuration information.
  • the second module is configured to send commands to different nodes to poll several backend service endpoints on their respective nodes at regular intervals to obtain The topology information of different nodes, the health status and link quality of several back-end service endpoints;
  • the third module is configured to calculate the priority of several back-end service endpoints based on the topology information, health status and link quality, and based on priority setting service response endpoints for load balancing; and a fourth module configured to recalculate priorities of several backend service endpoints in response to changes in topology information and/or changes in health status and/or link quality, and Adjust service response endpoints based on priority.
  • a computer device including: at least one processor; and a memory, the memory stores computer instructions that can be run on the processor, and when the instructions are executed by the processor, the above method is implemented. step.
  • This application has the following beneficial technical effects: solve the problem that the load balancing performance is not high in a large-scale data center environment, and the problem that the link cannot be adjusted in real time according to the topology status of the load balancing back-end service endpoint, through the topology of the load balancer back-end service endpoint Perception, and adjust load balancing according to topology perception results, optimize load balancing performance, and greatly improve network bandwidth resource utilization and user experience.
  • FIG. 1 is a schematic diagram of an embodiment of a topology-aware load balancing method provided by the present application
  • FIG. 2 is a schematic diagram of an embodiment of a topology-aware load balancing device provided by the present application
  • Fig. 3 is a schematic diagram of an embodiment of a computer device provided by the present application.
  • FIG. 1 is a schematic diagram of an embodiment of a topology-aware load balancing method provided by the present application.
  • the embodiment of the present application includes, for example, performing the following steps in the control module:
  • the load balancer can adjust the link according to the latest topology information collected, greatly improving the utilization of network bandwidth resources and user experience.
  • the topology-aware load balancing mainly includes a topology-aware module, a control module, a health detection module and an event processing module.
  • the control module is responsible for the distribution of user-configured load balancing rules and the presentation of load balancing services.
  • the control module is the central module of the entire system.
  • the control module interacts with the topology perception module, health detection module and event processing module at the same time, and intelligently analyzes according to the interaction results And automatically select the load balancing backend service endpoint of the optimal link to provide services for load balancing.
  • the topology perception module is responsible for perceiving the topology information of the backend service endpoint according to the backend service endpoint information issued by the control module, and sends the perceived topology information to the control module through the event processing module, and the topology perception module also perceives the topology of the backend service endpoint When the BACKEND topology changes, the topology awareness module will send the new topology to the control module through the event processing module.
  • the topology awareness module will be enabled on the node when the load balancing function is enabled, but only the node where the backend service endpoint Topology event information will be reported.
  • the health detection module is responsible for performing health detection based on the backend service endpoint information issued by the control module. It should be noted that the control module can perceive the health status and link status of the backend service endpoint according to the detection results of the health detection module.
  • the event processing module is responsible for the generation and processing of events, and is a channel for message transmission between various modules.
  • the user enables the load balancing function and configures the back-end service endpoints according to the needs.
  • the control module After receiving the user's load balancing configuration information, the rules are issued to the nodes according to the configuration information: if the load balancing backend service endpoint is located on the same node, there is no need to poll the backend service endpoint according to the topology information reported by the topology awareness module ; If the load balancing backend service endpoints are located on different nodes, the control module first polls the backend service endpoints according to the health status of the backend service endpoints sent by the health detection module to ensure that the load balancing service is available immediately.
  • the perception module starts to perceive and upload the topology information of the backend service endpoints to the control module.
  • the control module obtains the topology information of the backend service endpoints sent by all nodes, according to the topology information of the backend service endpoints and the health report of the backend service endpoints Health status and link quality, comprehensive calculation to select the optimal back-end service endpoint and adjust the priority of each back-end service endpoint, so as to realize the preferential selection of the back-end service endpoint with the best topology and link quality as the service response of load balancing endpoint.
  • the topology detection module reports the new topology relationship, and the control module recalculates whether the backend service endpoint needs to be adjusted according to the latest topology information and health detection information. to achieve the best network performance.
  • the present application also includes: the topology perception modules of different nodes perform regular polling on several backend service endpoints on respective nodes, so as to obtain topology information of different nodes, and upload the topology information to the control module;
  • the health monitoring modules of different nodes periodically poll several back-end service endpoints on their respective nodes to obtain the health status and link information of several back-end service endpoints, and upload the health status and link information to the control module.
  • responding to changes in topology information and/or changes in health status and/or link quality includes: obtaining current topology information by a topology perception module, and judging the difference between the current topology information and the topology obtained last time Whether the information is the same; if the current topology information is different from the topology information obtained last time, confirm that the topology information has changed, and upload the current topology information to the control module; the health monitoring module obtains the current health status and current link information, and uploads the current The health status and current link information are uploaded to the control module, and the control module judges whether the health status and link quality have changed based on the current health status and current link information and the health status and link information obtained last time.
  • the topology awareness module perceives the backend service endpoint topology information on the node according to the received load balancing backend service endpoint information, and sends the perceived topology information to the control module through the event processing module. At the same time, if When the topology of the backend service endpoint on the current node changes, the topology awareness event will re-report the changed topology relationship to the control module.
  • the health detection module is responsible for detecting the health status of the load balancing backend service endpoint. At the same time, the health detection module also obtains the network link status information of the backend service endpoint, and finally sends the detection information to the The control module is processed uniformly by the control module.
  • it further includes: if the current topology information is the same as the topology information obtained last time, and confirming that the topology information has not changed, then the current topology information will not be uploaded to the control module.
  • the topology awareness module perceives the backend service endpoint topology information on the node according to the received load balancing backend service endpoint information. Do not report the topology relationship of the back-end service endpoints to reduce system load and save network bandwidth resources.
  • calculating the priority of several backend service endpoints includes: calculating the average link cost based on the link cost in the link quality, and based on Link average cost, topology weight, link weight, link cost weight, link stability weight, and delay change weight are calculated to obtain the load balancing priority of several backend service endpoints.
  • calculating load balancing priorities of several backend service endpoints based on link average cost, topology weight, link weight, link cost weight, link stability weight, and delay change weight includes: The priority of several backend service endpoints is calculated by the following formula:
  • a 1 is the topology weight of topology T
  • a 2 is the link weight
  • x 1 , x 2 ,..., x n is the link cost of the corresponding link
  • a 3 is the link cost weight
  • a 4 is the link weight
  • L is the delay change weight
  • M is the average cost of the link.
  • the average link cost M is calculated using the following method:
  • x 1 , x 2 , ..., x n are the link costs of the corresponding links.
  • the calculation method of the load balancing priority P is as follows:
  • setting priority-based service response endpoints for load balancing includes: sorting the priorities of several back-end service endpoints from high to low, and using the highest-priority back-end service endpoint as the load balancing The service response endpoint for .
  • adjusting the service response endpoint based on the priority includes: sorting the recalculated priorities of several backend service endpoints from high to low, and sorting the recalculated priority of the highest priority backend service
  • the endpoint acts as a load-balanced service response endpoint.
  • each step in each embodiment of the above-mentioned topology-aware load balancing method can be interleaved, replaced, added, and deleted. It should belong to the protection scope of the present application, and should not limit the protection scope of the present application to the embodiment.
  • FIG. 2 is a schematic diagram of an embodiment of a topology-aware load balancing device provided by the present application.
  • the embodiment of the present application includes the following modules: the first module S11 is configured to obtain the load balancing configuration information issued by the user, and judge whether the several backend service endpoints of the load balancing are located at different nodes based on the configuration information; The second module S12 is configured to, if several back-end service endpoints of load balancing are located on different nodes, periodically send commands to different nodes to poll several back-end service endpoints on respective nodes, so as to obtain topology information of different nodes, several The health status and link quality of the back-end service endpoints; the third module S13 is configured to calculate the priority of several back-end service endpoints based on topology information, health status and link quality, and set the balance load based on the priority
  • FIG. 3 is a schematic diagram of an embodiment of a computer device provided by the present application.
  • the embodiment of the present application includes the following devices: at least one processor S21; and a memory S22, the memory S22 stores computer instructions S23 that can run on the processor, and the steps of the above method are implemented when the instructions are executed by the processor .
  • the program of the topology-aware load balancing method can be stored in a computer.
  • the program When the program is read from the storage medium, when executed, it may include the processes of the embodiments of the above-mentioned methods.
  • the storage medium of the program may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), and the like.
  • ROM read-only memory
  • RAM random access memory
  • the method disclosed according to the embodiment of the present application may also be implemented as a computer program executed by a processor, and the computer program may be stored in a computer-readable storage medium.
  • the computer program is executed by the processor, the above-mentioned functions defined in the methods disclosed in the embodiments of the present application are executed.
  • the above-mentioned method steps and system units can also be realized by using a controller and a computer-readable storage medium for storing a computer program for enabling the controller to realize the functions of the above-mentioned steps or units.
  • functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
  • Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer.
  • the computer readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage device, magnetic disk storage device or other magnetic storage device, or may be used to carry or store instructions in Any other medium that can be accessed by a general purpose or special purpose computer or a general purpose or special purpose processor, and the required program code or data structure. Also, any connection is properly termed a computer-readable medium.
  • Disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers . Combinations of the above should also be included within the scope of computer-readable media.
  • the storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请公开了一种拓扑感知的负载均衡方法，包括：获取用户下发的负载均衡配置信息，并基于配置信息判断负载均衡的若干后端服务端点是否位于不同节点；若是负载均衡的若干后端服务端点位于不同节点，向不同节点定时下发对各自节点上若干后端服务端点轮询的命令，以获取不同节点的拓扑信息、后端服务端点的健康状态和链路质量；基于拓扑信息、健康状态和链路质量，计算得到后端服务端点的优先级，并基于优先级设置均衡负载的服务响应端点；以及响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化，重新计算后端服务端点的优先级，并基于优先级调整服务响应端点。本申请还公开了一种拓扑感知的负载均衡装置和计算机设备。

Description

一种拓扑感知的负载均衡方法、装置及计算机设备
本申请要求在2021年7月8日提交中国专利局、申请号为202110771506.2、发明名称为“一种拓扑感知的负载均衡方法、装置及计算机设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及负载均衡技术领域，尤其涉及一种拓扑感知的负载均衡方法、装置及设备。
背景技术
在云计算时代，业务改造上也不断地开展，伴随着云计算的不断发展，云计算数据中心规模越来越大，在大规模数据中心环境下通过合理规划、技术优化使在硬件资产固定的情况下单位计算资源所承载的计算密度越来越高，而在硬件资产固定的情况下网络带宽资源也是固定的，数据中心的网络带宽资源越来越珍贵，如何合理高效的利用固定的网络带宽资源为用户提供最优质的服务是当前数据中心亟需解决的问题。
传统的负载均衡策略无法感知负载均衡后端服务端点的拓扑信息，导致两个问题：第一，负载均衡系统无法有效、合理的规划后端服务端点资源，导致为负载均衡前端提供服务的后端服务端点不是最优的，用户体验差、不能合理利用数据中心资源；第二，用户可以通过合理规划负载均衡后端服务端点的拓扑，以达到系统最优，但是当负载均衡后端服务端点拓扑因故障、计算资源不足等问题而导致变动，系统无法自动调整负载均衡规则，而需要运维人员根据新的拓扑手动重新调整，导致出错风险大、运维成本高。
发明内容
有鉴于此，本申请实施例的目的在于提出一种拓扑感知的负载均衡方法、装置及计算机设备，使用拓扑感知与链路质量感知的方式根据优先级算法计算负载均衡后端服务端点的优先级，选择最优后端服务端点作为负载均衡服务后端，同时当网络状态发生变化或后端服务端点拓扑发生变化时负载均衡可以自动适配最新的拓扑与链路状态，在不升级硬件的基础上充分利用了数据中心网络链路带宽资源为用户带来最好的使用体验，同时能够实时感知后端服务端点拓扑状态变化与网络链路质量变化，及时调整负载均衡后端服务端点的优先级，始终优先选择最优后端服务端点为负载均衡提供服务。避免了传统负载均衡器无法感知后端服务端点拓扑与链路质量的缺陷同时也避免了管理员手动调整带来的繁琐工作与变更风险。
基于上述目的，本申请实施例的一方面提供了一种拓扑感知的负载均衡方法，包括以下步骤：获取用户下发的负载均衡配置信息，并基于配置信息判断负载均衡的若干后端服务端点是否位于不同节点；若是负载均衡的若干后端服务端点位于不同节点，向不同节点定时下发对各自节点上若干后端服务端点轮询的命令，以获取不同节点的拓扑信息、若干后端服务端点的健康状态和链路质量；基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级，并基于优先级设置均衡负载的服务响应端点；以及响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化，重新计算若干后端服务端点的优先级，并基于优先级调整服务响应端点。
在一些实施方式中，还包括：由不同节点的拓扑感知模块对各自节点上若干后端服务端点进行定时轮询，以获取不同节点的拓扑信息，并将拓扑信息上传到控制模块；由不同节点的健康监测模块对各自节点上若干后端服务端点进行定时轮询，以获取若干后端服务端点的健康状态和链路信息，并将健康状态和链路信息上传到控制模块。
在一些实施方式中，响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化包括：由拓扑感知模块获取当前拓扑信息，并判断当前拓扑信息与上次获取的拓扑信息是否相同；若是当前拓扑信息与上次获取的拓扑信息不同，确认拓扑信息发生变化，并将当前拓扑信息上传到控制模块；由 健康监测模块获取当前健康状态和当前链路信息，并将当前健康状态和当前链路信息上传到控制模块，并由控制模块基于当前健康状态和当前链路信息与上次获取的健康状态和链路信息判断健康状态和链路质量是否发生变化。
在一些实施方式中，还包括：若是当前拓扑信息与上次获取的拓扑信息相同，确认拓扑信息未发生变化，则不会将当前拓扑信息上传到控制模块。
在一些实施方式中，基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级包括：基于链路质量中的链路开销计算得到链路平均开销，并基于链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到若干后端服务端点的负载均衡优先级。
在一些实施方式中，基于链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到若干后端服务端点的负载均衡优先级包括：通过如下公式计算若干后端服务端点的优先级：
Figure PCTCN2021121912-appb-000001
其中，A 1为拓扑T的拓扑权重，A 2为链路权重，x 1，x 2，……，x n为对应链路的链路开销，A 3为链路开销权重，A 4为链路稳定性权重，L为延迟变更权重，M为链路平均开销。
在一些实施方式中，基于优先级设置均衡负载的服务响应端点包括：将若干后端服务端点的优先级按照从高到低排序，并将优先级最高的后端服务端点作为负载均衡的服务响应端点。
在一些实施方式中，基于优先级调整服务响应端点包括：将若干后端服务端点重新计算得到的优先级按照从高到低排序，并将重新计算得到的优先级最高的后端服务端点作为负载均衡的服务响应端点。
本申请实施例的另一方面，还提供了一种拓扑感知的负载均衡装置，包括：第一模块，配置用于获取用户下发的负载均衡配置信息，并基于配置信息判断负载均衡的若干后端服务端点是否位于不同节点；第二模块，配置用 于若是负载均衡的若干后端服务端点位于不同节点，向不同节点定时下发对各自节点上若干后端服务端点轮询的命令，以获取不同节点的拓扑信息、若干后端服务端点的健康状态和链路质量；第三模块，配置用于基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级，并基于优先级设置均衡负载的服务响应端点；以及第四模块，配置用于响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化，重新计算若干后端服务端点的优先级，并基于优先级调整服务响应端点。
本申请实施例的再一方面，还提供了一种计算机设备，包括：至少一个处理器；以及存储器，存储器存储有可在处理器上运行的计算机指令，指令由处理器执行时实现上述方法的步骤。
本申请具有以下有益技术效果：解决大规模数据中心环境下负载均衡性能不高、无法实时根据负载均衡后端服务端点拓扑状态调整链路的问题，通过对负载均衡器后端服务端点的拓扑进行感知，并根据拓扑感知结果调整负载均衡，实现负载均衡性能最优化，极大提升网络带宽资源利用率与用户使用体验。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的实施例。
图1为本申请提供的拓扑感知的负载均衡方法的实施例的示意图；
图2为本申请提供的拓扑感知的负载均衡装置的实施例的示意图；
图3为本申请提供的计算机设备的实施例的示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白，以下结合具体实施例，并参照附图，对本申请实施例进一步详细说明。
需要说明的是，本申请实施例中所有使用“第一”和“第二”的表述均是为了区分两个相同名称非相同的实体或者非相同的参量，可见“第一”“第二”仅为了表述的方便，不应理解为对本申请实施例的限定，后续实施例对此不再一一说明。
基于上述目的，本申请实施例的第一个方面，提出了拓扑感知的负载均衡方法的实施例。图1示出的是本申请提供的拓扑感知的负载均衡方法的实施例的示意图。如图1所示，本申请实施例包括例如在控制模块中执行如下步骤：
S01、获取用户下发的负载均衡配置信息，并基于配置信息判断负载均衡的若干后端服务端点是否位于不同节点；
S02、若是负载均衡的若干后端服务端点位于不同节点，向不同节点定时下发对各自节点上若干后端服务端点轮询的命令，以获取不同节点的拓扑信息、若干后端服务端点的健康状态和链路质量；
S03、基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级，并基于优先级设置均衡负载的服务响应端点；以及
S04、响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化，重新计算若干后端服务端点的优先级，并基于优先级调整服务响应端点。
在本实施例中，主要应用于大规模数据中心环境下的负载均衡，对负载均衡后端服务端点的拓扑进行感知，根据拓扑感知结果调整负载均衡提供服务的后端服务端点，实现负载均衡性能最优化。当后端服务端点因故障、计算资源等问题导致拓扑改变时，负载均衡器可以根据收集到的最新拓扑信息调整链路，极大提升网络带宽资源利用率与用户使用体验。
在本实施例中，拓扑感知的负载均衡主要包括拓扑感知模块、控制模块、健康检测模块与事件处理模块。控制模块负责完成用户配置负载均衡规则的下发与负载均衡服务的呈现，控制模块是整个系统的中枢模块，控制模块同时与拓扑感知模块、健康检测模块与事件处理模块交互，根据交互结果智能分析并自动选择最优链路的负载均衡后端服务端点为负载均衡提供服务。 拓扑感知模块根据控制模块下发的后端服务端点信息负责感知后端服务端点的拓扑信息，并将感知到的拓扑信息通过事件处理模块发送到控制模块，拓扑感知模块还感知后端服务端点拓扑变化，当感知到BACKEND拓扑发生变化，拓扑感知模块将新的拓扑通过事件处理模块发送到控制模块，拓扑感知模块在启用负载均衡功能时在节点上启用，但仅有后端服务端点所在节点才会上报拓扑事件信息。健康检测模块负责根据控制模块下发的后端服务端点信息进行健康检测，需要说明的是，控制模块可以根据健康检测模块检测结果感知后端服务端点的健康状态与链路状态。事件处理模块负责事件的产生与处理，是各个模块之间消息传递的通道。
在本实施例中，用户根据需要开启负载均衡功能并配置后端服务端点，一般情况下，出于灾备、高可用等因素考虑，不同的后端服务端点会选择不同的节点部署；控制模块收到用户的负载均衡配置信息，根据配置信息下发规则到节点：若负载均衡后端服务端点位于同一节点，则不需要根据拓扑感知模块上报的拓扑信息，对后端服务端点进行轮询处理；若负载均衡后端服务端点位于不同节点，控制模块首先根据健康检测模块上送的后端服务端点健康状态对后端服务端点进行轮询处理以保证负载均衡服务即时可用，同时节点上的拓扑感知模块开始感知并上传后端服务端点的拓扑信息到控制模块，当控制模块获取到所有节点上送的后端服务端点拓扑信息后根据后端服务端点的拓扑信息与健康上报的后端服务端点健康状态与链路质量，综合计算选择最优的后端服务端点并调整各个后端服务端点的优先级，从而实现优先选择拓扑与链路质量最佳的后端服务端点作为负载均衡的服务响应端点。
在本实施例中，若系统运行过程中负载均衡后端服务端点拓扑发生变化，拓扑检测模块上报新的拓扑关系，控制模块根据最新的拓扑信息与健康检测信息重新计算是否需要调整后端服务端点的优先级以到达最佳网络性能。
在本申请的一些实施例中，还包括：由不同节点的拓扑感知模块对各自节点上若干后端服务端点进行定时轮询，以获取不同节点的拓扑信息，并将 拓扑信息上传到控制模块；由不同节点的健康监测模块对各自节点上若干后端服务端点进行定时轮询，以获取若干后端服务端点的健康状态和链路信息，并将健康状态和链路信息上传到控制模块。
在本申请的一些实施例中，响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化包括：由拓扑感知模块获取当前拓扑信息，并判断当前拓扑信息与上次获取的拓扑信息是否相同；若是当前拓扑信息与上次获取的拓扑信息不同，确认拓扑信息发生变化，并将当前拓扑信息上传到控制模块；由健康监测模块获取当前健康状态和当前链路信息，并将当前健康状态和当前链路信息上传到控制模块，并由控制模块基于当前健康状态和当前链路信息与上次获取的健康状态和链路信息判断健康状态和链路质量是否发生变化。
在本实施例中，拓扑感知模块根据收到负载均衡后端服务端点信息感知节点上的后端服务端点拓扑信息，并将感知到的拓扑信息通过事件处理模块上送到控制模块，同时，若当前节点上的后端服务端点发生拓扑变化，拓扑感知事件将变化后的拓扑关系重新上报控制模块。
在本实施例中，健康检测模块负责检测负载均衡后端服务端点的健康状态，同时，健康检测模块也同时获取后端服务端点的网络链路状态信息，最终将检测信息通过事件处理模块发送到控制模块，由控制模块统一处理。
在本申请的一些实施例中，还包括：若是当前拓扑信息与上次获取的拓扑信息相同，确认拓扑信息未发生变化，则不会将当前拓扑信息上传到控制模块。
在本实施例中，拓扑感知模块根据收到负载均衡后端服务端点信息感知节点上的后端服务端点拓扑信息，若当前节点上的拓扑无变化时，拓扑感知模块进入静默模式，仅仅收集但不上报后端服务端点拓扑关系，以减小系统负载、节省网络带宽资源。
在本申请的一些实施例中，基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级包括：基于链路质量中的链路开销计算得 到链路平均开销，并基于链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到若干后端服务端点的负载均衡优先级。
在本申请的一些实施例中，基于链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到若干后端服务端点的负载均衡优先级包括：通过如下公式计算若干后端服务端点的优先级：
Figure PCTCN2021121912-appb-000002
其中，A 1为拓扑T的拓扑权重，A 2为链路权重，x 1，x 2，……，x n为对应链路的链路开销，A 3为链路开销权重，A 4为链路稳定性权重，L为延迟变更权重，M为链路平均开销。
在本实施例中，链路平均开销M使用以下方式计算：
Figure PCTCN2021121912-appb-000003
其中，x 1，x 2，……，x n为对应链路的链路开销。
在本实施例中，以三个节点为例，负载均衡优先级P的计算方式如下：
Figure PCTCN2021121912-appb-000004
Figure PCTCN2021121912-appb-000005
在本申请的一些实施例中，基于优先级设置均衡负载的服务响应端点包括：将若干后端服务端点的优先级按照从高到低排序，并将优先级最高的后端服务端点作为负载均衡的服务响应端点。
在本申请的一些实施例中，基于优先级调整服务响应端点包括：将若干后端服务端点重新计算得到的优先级按照从高到低排序，并将重新计算得到的优先级最高的后端服务端点作为负载均衡的服务响应端点。
需要特别指出的是，上述拓扑感知的负载均衡方法的各个实施例中的各个步骤均可以相互交叉、替换、增加、删减，因此，这些合理的排列组合 变换之于拓扑感知的负载均衡方法也应当属于本申请的保护范围，并且不应将本申请的保护范围局限在实施例之上。
基于上述目的，本申请实施例的第二个方面，提出了一种拓扑感知的负载均衡装置。图2示出的是本申请提供的拓扑感知的负载均衡装置的实施例的示意图。如图2所示，本申请实施例包括如下模块：第一模块S11，配置用于获取用户下发的负载均衡配置信息，并基于配置信息判断负载均衡的若干后端服务端点是否位于不同节点；第二模块S12，配置用于若是负载均衡的若干后端服务端点位于不同节点，向不同节点定时下发对各自节点上若干后端服务端点轮询的命令，以获取不同节点的拓扑信息、若干后端服务端点的健康状态和链路质量；第三模块S13，配置用于基于拓扑信息、健康状态和链路质量，计算得到若干后端服务端点的优先级，并基于优先级设置均衡负载的服务响应端点；以及第四模块S14，配置用于响应于拓扑信息发生变化和/或健康状态和/或链路质量发生变化，重新计算若干后端服务端点的优先级，并基于优先级调整服务响应端点。
基于上述目的，本申请实施例的第三个方面，提出了一种计算机设备。图3示出的是本申请提供的计算机设备的实施例的示意图。如图3所示，本申请实施例包括如下装置：至少一个处理器S21；以及存储器S22，存储器S22存储有可在处理器上运行的计算机指令S23，指令由处理器执行时实现以上方法的步骤。
最后需要说明的是，本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，可以通过计算机程序来指令相关硬件来完成，拓扑感知的负载均衡方法的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，程序的存储介质可为磁碟、光盘、只读存储记忆体(ROM)或随机存储记忆体(RAM)等。上述计算机程序的实施例，可以达到与之对应的前述任意方法实施例相同或者相类似的效果。
此外，根据本申请实施例公开的方法还可以被实现为由处理器执行的计算机程序，该计算机程序可以存储在计算机可读存储介质中。在该计算机 程序被处理器执行时，执行本申请实施例公开的方法中限定的上述功能。
此外，上述方法步骤以及系统单元也可以利用控制器以及用于存储使得控制器实现上述步骤或单元功能的计算机程序的计算机可读存储介质实现。
本领域技术人员还将明白的是，结合这里的公开所描述的各种示例性逻辑块、模块、电路和算法步骤可以被实现为电子硬件、计算机软件或两者的组合。为了清楚地说明硬件和软件的这种可互换性，已经就各种示意性组件、方块、模块、电路和步骤的功能对其进行了一般性的描述。这种功能是被实现为软件还是被实现为硬件取决于具体应用以及施加给整个系统的设计约束。本领域技术人员可以针对每种具体应用以各种方式来实现的功能，但是这种实现决定不应被解释为导致脱离本申请实施例公开的范围。
在一个或多个示例性设计中，功能可以在硬件、软件、固件或其任意组合中实现。如果在软件中实现，则可以将功能作为一个或多个指令或代码存储在计算机可读介质上或通过计算机可读介质来传送。计算机可读介质包括计算机存储介质和通信介质，该通信介质包括有助于将计算机程序从一个位置传送到另一个位置的任何介质。存储介质可以是能够被通用或专用计算机访问的任何可用介质。作为例子而非限制性的，该计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其它光盘存储设备、磁盘存储设备或其它磁性存储设备，或者是可以用于携带或存储形式为指令或数据结构的所需程序代码并且能够被通用或专用计算机或者通用或专用处理器访问的任何其它介质。此外，任何连接都可以适当地称为计算机可读介质。例如，如果使用同轴线缆、光纤线缆、双绞线、数字用户线路(DSL)或诸如红外线、无线电和微波的无线技术来从网站、服务器或其它远程源发送软件，则上述同轴线缆、光纤线缆、双绞线、DSL或诸如红外线、无线电和微波的无线技术均包括在介质的定义。如这里所使用的，磁盘和光盘包括压缩盘(CD)、激光盘、光盘、数字多功能盘(DVD)、软盘、蓝光盘，其中磁盘通常磁性地再现数据，而光盘利用激光光学地再现数据。上述内容的组合也应当包括在计算机可读介质的范围内。
以上是本申请公开的示例性实施例，但是应当注意，在不背离权利要求限定的本申请实施例公开的范围的前提下，可以进行多种改变和修改。根据这里描述的公开实施例的方法权利要求的功能、步骤和/或动作不需以任何特定顺序执行。此外，尽管本申请实施例公开的元素可以以个体形式描述或要求，但除非明确限制为单数，也可以理解为多个。
应当理解的是，在本文中使用的，除非上下文清楚地支持例外情况，单数形式“一个”旨在也包括复数形式。还应当理解的是，在本文中使用的“和/或”是指包括一个或者一个以上相关联地列出的项目的任意和所有可能组合。
上述本申请实施例公开实施例序号仅仅为了描述，不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
所属领域的普通技术人员应当理解：以上任何实施例的讨论仅为示例性的，并非旨在暗示本申请实施例公开的范围(包括权利要求)被限于这些例子；在本申请实施例的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，并存在如上的本申请实施例的不同方面的许多其它变化，为了简明它们没有在细节中提供。因此，凡在本申请实施例的精神和原则之内，所做的任何省略、修改、等同替换、改进等，均应包含在本申请实施例的保护范围之内。

Claims (10)

  1. 一种拓扑感知的负载均衡方法，其特征在于，包括以下步骤：
    获取用户下发的负载均衡配置信息，并基于所述配置信息判断负载均衡的若干后端服务端点是否位于不同节点；
    若是负载均衡的若干后端服务端点位于不同节点，向所述不同节点定时下发对各自节点上所述若干后端服务端点轮询的命令，以获取所述不同节点的拓扑信息、所述若干后端服务端点的健康状态和链路质量；
    基于所述拓扑信息、所述健康状态和所述链路质量，计算得到所述若干后端服务端点的优先级，并基于所述优先级设置均衡负载的服务响应端点；以及
    响应于所述拓扑信息发生变化和/或所述健康状态和/或所述链路质量发生变化，重新计算所述若干后端服务端点的优先级，并基于所述优先级调整所述服务响应端点。
  2. 根据权利要求1所述的拓扑感知的负载均衡方法，其特征在于，还包括：
    由所述不同节点的拓扑感知模块对各自节点上所述若干后端服务端点进行定时轮询，以获取所述不同节点的拓扑信息，并将所述拓扑信息上传到控制模块；
    由所述不同节点的健康监测模块对各自节点上所述若干后端服务端点进行定时轮询，以获取所述若干后端服务端点的健康状态和链路信息，并将所述健康状态和所述链路信息上传到所述控制模块。
  3. 根据权利要求2所述的拓扑感知的负载均衡方法，其特征在于，响应于所述拓扑信息发生变化和/或所述健康状态和/或所述链路质量发生变化包括：
    由所述拓扑感知模块获取当前拓扑信息，并判断所述当前拓扑信息与上次获取的所述拓扑信息是否相同；
    若是所述当前拓扑信息与上次获取的所述拓扑信息不同，确认所述拓扑 信息发生变化，并将所述当前拓扑信息上传到所述控制模块；
    由所述健康监测模块获取当前健康状态和当前链路信息，并将所述当前健康状态和所述当前链路信息上传到所述控制模块，并由所述控制模块基于所述当前健康状态和所述当前链路信息与上次获取的健康状态和链路信息判断所述健康状态和所述链路质量是否发生变化。
  4. 根据权利要求3所述的拓扑感知的负载均衡方法，其特征在于，还包括：
    若是所述当前拓扑信息与上次获取的所述拓扑信息相同，确认所述拓扑信息未发生变化，则不会将所述当前拓扑信息上传到所述控制模块。
  5. 根据权利要求1所述的拓扑感知的负载均衡方法，其特征在于，基于所述拓扑信息、所述健康状态和所述链路质量，计算得到所述若干后端服务端点的优先级包括：
    基于所述链路质量中的链路开销计算得到链路平均开销，并基于所述链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到所述若干后端服务端点的负载均衡优先级。
  6. 根据权利要求5所述的拓扑感知的负载均衡方法，其特征在于，基于所述链路平均开销、拓扑权重、链路权重、链路开销权重、链路稳定性权重、延迟变更权重计算得到所述若干后端服务端点的负载均衡优先级包括：
    通过如下公式计算所述若干后端服务端点的优先级：
    Figure PCTCN2021121912-appb-100001
    其中，A 1为拓扑T的拓扑权重，A 2为链路权重，x 1，x 2，……，x n为对应链路的链路开销，A 3为链路开销权重，A 4为链路稳定性权重，L为延迟变更权重，M为链路平均开销。
  7. 根据权利要求1所述的拓扑感知的负载均衡方法，其特征在于，基于优先级设置均衡负载的服务响应端点包括：
    将所述若干后端服务端点的优先级按照从高到低排序，并将优先级最高 的所述后端服务端点作为负载均衡的服务响应端点。
  8. 根据权利要求1所述的拓扑感知的负载均衡方法，其特征在于，基于优先级调整所述服务响应端点包括：
    将所述若干后端服务端点重新计算得到的优先级按照从高到低排序，并将重新计算得到的优先级最高的所述后端服务端点作为负载均衡的服务响应端点。
  9. 一种拓扑感知的负载均衡装置，其特征在于，包括：
    第一模块，配置用于获取用户下发的负载均衡配置信息，并基于所述配置信息判断负载均衡的若干后端服务端点是否位于不同节点；
    第二模块，配置用于若是负载均衡的若干后端服务端点位于不同节点，向所述不同节点定时下发对各自节点上所述若干后端服务端点轮询的命令，以获取所述不同节点的拓扑信息、所述若干后端服务端点的健康状态和链路质量；
    第三模块，配置用于基于所述拓扑信息、所述健康状态和所述链路质量，计算得到所述若干后端服务端点的优先级，并基于所述优先级设置均衡负载的服务响应端点；以及
    第四模块，配置用于响应于所述拓扑信息发生变化和/或所述健康状态和/或所述链路质量发生变化，重新计算所述若干后端服务端点的优先级，并基于所述优先级调整所述服务响应端点。
  10. 一种计算机设备，其特征在于，包括：
    至少一个处理器；以及
    存储器，所述存储器存储有可在所述处理器上运行的计算机指令，所述指令由所述处理器执行时实现权利要求1-8任意一项所述方法的步骤。
PCT/CN2021/121912 2021-07-08 2021-09-29 一种拓扑感知的负载均衡方法、装置及计算机设备 WO2023279555A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/271,456 US11902362B2 (en) 2021-07-08 2021-09-29 Topology-aware load balancing method and apparatus, and computer device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110771506.2 2021-07-08
CN202110771506.2A CN113225403B (zh) 2021-07-08 2021-07-08 一种拓扑感知的负载均衡方法、装置及计算机设备

Publications (1)

Publication Number Publication Date
WO2023279555A1 true WO2023279555A1 (zh) 2023-01-12

Family

ID=77081180

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/121912 WO2023279555A1 (zh) 2021-07-08 2021-09-29 一种拓扑感知的负载均衡方法、装置及计算机设备

Country Status (3)

Country Link
US (1) US11902362B2 (zh)
CN (1) CN113225403B (zh)
WO (1) WO2023279555A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115996176A (zh) * 2023-03-24 2023-04-21 广州世炬网络科技有限公司 节点拓扑结构调整方法及装置
CN116700993A (zh) * 2023-08-02 2023-09-05 浪潮(北京)电子信息产业有限公司 一种负载均衡方法、装置、设备及可读存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113225403B (zh) * 2021-07-08 2021-08-31 苏州浪潮智能科技有限公司 一种拓扑感知的负载均衡方法、装置及计算机设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050105475A1 (en) * 2002-03-04 2005-05-19 Joakim Norrgard Method for providing topology awareness information within an ip network
US20100333104A1 (en) * 2009-06-26 2010-12-30 Microsoft Corporation Service-Based Endpoint Discovery for Client-Side Load Balancing
CN110035468A (zh) * 2019-03-26 2019-07-19 北京宇航系统工程研究所 高可靠高安全无线网络拓扑控制系统
CN110838944A (zh) * 2019-11-15 2020-02-25 浪潮云信息技术有限公司 一种云中心租户维度拓扑图的实现方法
CN112929408A (zh) * 2021-01-19 2021-06-08 郑州阿帕斯数云信息科技有限公司 动态负载均衡方法及装置
CN113225403A (zh) * 2021-07-08 2021-08-06 苏州浪潮智能科技有限公司 一种拓扑感知的负载均衡方法、装置及计算机设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1398907B1 (de) * 2002-09-10 2010-12-08 Siemens Aktiengesellschaft Verfahren zur Kontrolle von Übertragungsressourcen eines paketorientierten Kommunikationsnetzes bei Topologieänderungen
US7561526B2 (en) * 2002-12-17 2009-07-14 Nortel Networks Limited Communication network route determination
CN101547139B (zh) * 2008-03-28 2012-03-07 华为技术有限公司 网络拓扑变化的通告方法及装置
US8458210B2 (en) * 2011-05-06 2013-06-04 Verizon Patent And Licensing Inc. Database load balancing through dynamic database routing
CN103685054B (zh) * 2013-12-18 2017-02-01 武汉烽火网络有限责任公司 基于业务感知的多路径负载均衡方法
US10853196B2 (en) * 2018-08-03 2020-12-01 EMC IP Holding Company LLC Prioritizing microservices on a container platform for a restore operation
US10999361B2 (en) * 2018-09-07 2021-05-04 Red Hat, Inc. Consistent hash-based load balancer
WO2022031835A1 (en) * 2020-08-05 2022-02-10 Avesha, Inc. Networked system for real-time computer-aided augmentation of live input video stream

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050105475A1 (en) * 2002-03-04 2005-05-19 Joakim Norrgard Method for providing topology awareness information within an ip network
US20100333104A1 (en) * 2009-06-26 2010-12-30 Microsoft Corporation Service-Based Endpoint Discovery for Client-Side Load Balancing
CN110035468A (zh) * 2019-03-26 2019-07-19 北京宇航系统工程研究所 高可靠高安全无线网络拓扑控制系统
CN110838944A (zh) * 2019-11-15 2020-02-25 浪潮云信息技术有限公司 一种云中心租户维度拓扑图的实现方法
CN112929408A (zh) * 2021-01-19 2021-06-08 郑州阿帕斯数云信息科技有限公司 动态负载均衡方法及装置
CN113225403A (zh) * 2021-07-08 2021-08-06 苏州浪潮智能科技有限公司 一种拓扑感知的负载均衡方法、装置及计算机设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LAN YUAN-LIANG; WANG KUOCHEN; HSU YI-HUAI: "Dynamic load-balanced path optimization in SDN-based data center networks", 2016 10TH INTERNATIONAL SYMPOSIUM ON COMMUNICATION SYSTEMS, NETWORKS AND DIGITAL SIGNAL PROCESSING (CSNDSP), IEEE, 20 July 2016 (2016-07-20), pages 1 - 6, XP032968145, DOI: 10.1109/CSNDSP.2016.7573945 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115996176A (zh) * 2023-03-24 2023-04-21 广州世炬网络科技有限公司 节点拓扑结构调整方法及装置
CN115996176B (zh) * 2023-03-24 2023-05-30 广州世炬网络科技有限公司 节点拓扑结构调整方法及装置
CN116700993A (zh) * 2023-08-02 2023-09-05 浪潮(北京)电子信息产业有限公司 一种负载均衡方法、装置、设备及可读存储介质
CN116700993B (zh) * 2023-08-02 2024-02-09 浪潮(北京)电子信息产业有限公司 一种负载均衡方法、装置、设备及可读存储介质

Also Published As

Publication number Publication date
CN113225403A (zh) 2021-08-06
US11902362B2 (en) 2024-02-13
US20230412674A1 (en) 2023-12-21
CN113225403B (zh) 2021-08-31

Similar Documents

Publication Publication Date Title
WO2023279555A1 (zh) 一种拓扑感知的负载均衡方法、装置及计算机设备
US11949588B2 (en) Large-scale real-time multimedia communications
US10715414B2 (en) Network communication methods and apparatus
US8667126B2 (en) Dynamic rate heartbeating for inter-node status updating
US8634328B2 (en) Endpoint-to-endpoint communications status monitoring
US10356185B2 (en) Optimal dynamic cloud network control
CN103685461B (zh) 一种集群管理装置、管理系统以及管理方法
EP3361703A1 (en) Load balancing method, related device and system
CA3083652C (en) Network capacity planning systems and methods
WO2023219669A1 (en) Intent-driven network analytics for predictive network slice management
Chekired et al. HybCon: A scalable SDN-based distributed cloud architecture for 5G networks
US10554324B1 (en) Dynamic wavelength allocation in optical networks
US12020017B2 (en) Method and electronic device for scheduling software upgrade of network devices
CN116455817A (zh) 一种软件定义云网融合架构及路由实现方法
US10447556B2 (en) End user on demand network resource instantiation
US20230131394A1 (en) Establishment of a telecommunications service
CN115202580A (zh) 一种多路径设备检测方法、装置、设备、存储介质
EP3675461B1 (en) Electronic communication node load balancing system and method
CN111106974B (zh) 一种测试无损网络性能的方法和装置
CN105812437A (zh) 一种业务分发方法、系统及相关装置
CN108600401A (zh) 一种数据传输方法及系统
US20240248763A1 (en) Arrangement system and arrangement method
KR20240099444A (ko) 네트워크에서의 모델 전송 상태 분석을 구독하는 방법, 장치 및 판독 가능 저장매체
JP2014007438A (ja) ノード管理装置、ノード管理方法、及びプログラム
JP2012010225A (ja) 情報通信システム、ノード装置、情報処理方法、及び情報処理プログラム

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: 21949042

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: 21949042

Country of ref document: EP

Kind code of ref document: A1