WO2016078461A1 - Path calculation method and path calculation server - Google Patents

Path calculation method and path calculation server Download PDF

Info

Publication number
WO2016078461A1
WO2016078461A1 PCT/CN2015/088044 CN2015088044W WO2016078461A1 WO 2016078461 A1 WO2016078461 A1 WO 2016078461A1 CN 2015088044 W CN2015088044 W CN 2015088044W WO 2016078461 A1 WO2016078461 A1 WO 2016078461A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
path
load information
integrated load
overloaded
Prior art date
Application number
PCT/CN2015/088044
Other languages
French (fr)
Chinese (zh)
Inventor
李辉
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
Publication of WO2016078461A1 publication Critical patent/WO2016078461A1/en

Links

Images

Definitions

  • This application relates to, but is not limited to, routing techniques.
  • Routing refers to the process by which a node in a network discovers one or more paths to a destination.
  • the routing process consists of the following parts: neighbor discovery, topology discovery, and path selection.
  • neighbor discovery nodes in the network can discover neighbor nodes adjacent to them and can know how they are connected to these neighbor nodes.
  • the role of topology discovery is to enable nodes to discover other nodes in the network and know how these nodes are connected.
  • the path calculation algorithm can be used to calculate the path from the source point to the sink point.
  • Routes in an optical network need to know the types and restrictions of different resources in the network.
  • resources are unavailable and connection cannot be established.
  • In its routing algorithm all possible paths can be calculated based on one or more constraints, and an optimal path is selected according to a certain strategy, thereby optimizing network performance.
  • a constraint of “rejecting specific network resources” is included, which excludes some network elements in the network from being used to calculate the optimal path according to the attributes of the nodes and links.
  • the constraint is judged only according to the state of the link, the reachability of the node, etc., and does not consider whether the actual load of the node itself (such as CPU usage, memory usage, etc.) is overloaded, in the actual routing process.
  • the actual load overload of a node that satisfies the constraint condition causes the service route to be processed in time or correctly through the node, the route fails, and the success rate of the path calculation is low.
  • This paper proposes a method for calculating paths and a path calculation server, which can improve the success rate of path calculation.
  • a method of calculating a path comprising:
  • the path calculation server acquires comprehensive load information of each node in advance
  • the path calculation server receives the path calculation request from the client, and calculates the path according to the integrated load information of each node.
  • the path calculation server calculates the path according to the integrated load information of each node, including:
  • the path calculation server determines whether each node is overloaded according to the obtained comprehensive load information of each node, and excludes the overloaded node, and calculates the path according to the constraint condition of the integrated load information that does not include the node;
  • the path calculation server calculates the path according to the integrated load information of each node, including:
  • the path calculation server calculates a path according to a constraint condition that does not include comprehensive load information of the node
  • the path calculation server determines whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, sends the calculated path to the client.
  • the method further includes:
  • the step of calculating the path according to the constraint that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded.
  • the integrated load information is an integrated load value or a level corresponding to the integrated load value.
  • the integrated load value is calculated according to one or more of the following:
  • the integrated load value is a weighted average between the CPU usage and the memory usage.
  • a path calculation server comprising:
  • the obtaining module is set to: obtain comprehensive load information of each node in advance;
  • the receiving module is configured to: receive a path calculation request from the client;
  • the calculation module is set to: calculate a path according to the integrated load information of each node.
  • the computing module is configured to:
  • the computing module is configured to:
  • a computer readable storage medium storing computer executable instructions for performing the method of any of the above.
  • the embodiment of the present invention includes: the path calculation server acquires the integrated load information of each node in advance; the path calculation server receives the path calculation request from the client, and calculates the path according to the integrated load information of each node. According to the solution of the embodiment of the present invention, the calculation of the path is performed according to the integrated load information of each node, so that the nodes on the calculated path have sufficient resources for routing processing, thereby improving the success rate of the path calculation.
  • FIG. 1 is a flowchart of a method for calculating a path according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a network according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of a method for a path calculation server to calculate a path when each node actively reports comprehensive load information in a network according to an embodiment of the present invention
  • FIG. 4 is a flowchart of a method for a path calculation server to calculate a path when the path calculation server actively queries the integrated load information of each node according to an embodiment of the present invention
  • FIG. 5 is a schematic structural diagram of a path calculation server according to an embodiment of the present invention.
  • an embodiment of the present invention provides a method for calculating a path, including:
  • Step 100 The path calculation server acquires comprehensive load information of each node in advance.
  • each node may periodically calculate the current integrated load information when receiving the query request from the path calculation server, and send the calculated integrated load information to the path calculation server; or, each node When it is determined that the integrated load information of the self changes, the calculated integrated load information is transmitted to the path calculation server.
  • the integrated load information may be a comprehensive load value or a level corresponding to the integrated load value.
  • the integrated load value may be calculated by one or more of the indicators related to the load of the node (such as CPU usage, number of processes waiting for resources, memory usage, throughput, number of interrupts, etc.), and may be used. The method is calculated and will not be described here.
  • the indicators related to the load of the node such as CPU usage, number of processes waiting for resources, memory usage, throughput, number of interrupts, etc.
  • the combined load value may be a weighted average between the CPU usage and the memory usage.
  • the level corresponding to the comprehensive load value can be set according to the actual situation.
  • Step 101 The path calculation server receives a path calculation request from the client, and calculates a path according to the integrated load information of each node.
  • This step includes:
  • the path calculation server determines whether each node is overloaded according to the obtained comprehensive load information of each node, and excludes the overloaded node, and calculates the path according to the constraint condition of the integrated load information that does not include the node; or, whether the node is overloaded or not included in the constraint condition Calculate the path in .
  • the path calculation server determines that the node is overloaded; if the integrated load value of the node is less than the preset threshold, the path calculation server determines that the node is not overloaded.
  • the path calculation server determines that the node is overloaded; if the level of the integrated load value of the node is less than the pre- If the level is set, the path calculation server determines that the node is not overloaded.
  • the path calculation server calculates the path according to the constraint condition that does not include the integrated load information of the node; the path calculation server determines whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, if not, Send the calculated path to the client. If the path calculation server determines that there is an overloaded node in the path, after the overloaded node is excluded, the step of calculating the path according to the constraint condition that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded. .
  • the path request server may send a query request to each node in the path to query the integrated load information of each node in the path.
  • calculating the path according to the constraint condition of the integrated load information that does not include the node means that the existing method is used to calculate the path without considering the comprehensive load information of each node in the network. Including whether a node is overloaded in a constraint, calculating a path refers to whether each node is overloaded as one of the constraints for path calculation.
  • FIG. 2 is a schematic structural diagram of a network. As shown in FIG. 2, the network is composed of 4 nodes and a path calculation server.
  • FIG. 3 is a flowchart of a method for a path calculation server to calculate a path when each node actively reports comprehensive load information in the network. As shown in FIG. 3, the method includes:
  • Step 300 Node 1, Node 2, Node 3, and Node 4 establish a connection with the path calculation server, and report their initial integrated load information P1, P2, P3, and P4 to the path calculation server.
  • the integrated load information is a level corresponding to the comprehensive load value, and the integration of the nodes can be performed.
  • the load value is divided into five levels for management.
  • the level 1 of the integrated load value indicates that the CPU usage is less than or equal to 20%
  • the level 2 indicates CPU usage is greater than 20% and less than or equal to 40%.
  • Level 3 indicates that the CPU usage is greater than 40% and less than or equal to 60%.
  • Level 4 indicates that the CPU usage is greater than 60% and less than or equal to 80%.
  • Level 5 indicates CPU usage. The rate is greater than 80%;
  • the initial integrated load information P1 of the node 1 is 3, the initial integrated load information P2 of the node 2 is 2, the initial integrated load information P3 of the node 3 is 1 level, and the initial integrated load information P4 of the node 4 is 2nd.
  • Step 301 The path calculation server receives and saves the integrated load information from each node.
  • Step 302 When the CPU usage of the node 1 reaches 85%, the comprehensive load information is changed to level 5, and the node 1 reports its own comprehensive load information P1 to the path calculation server again;
  • Step 303 After receiving the integrated load information P1 reported by the node 1, the path calculation server updates the value of the locally saved P1.
  • Step 304 The client initiates a path calculation request to the path calculation server.
  • Step 305 After receiving the path calculation request, the path calculation server acquires the comprehensive load information of each node stored locally, determines whether each node is overloaded according to the comprehensive load information of each node, and excludes the overloaded node.
  • Step 306 The path calculation server performs path calculation according to a constraint condition that does not include the integrated load information of the node.
  • Step 307 The path calculation server sends the calculated path information to the path calculation client.
  • FIG. 4 is a flowchart of a method for a path calculation server to calculate a path when the path calculation server actively queries the integrated load information of each node. As shown in FIG. 4, the method includes:
  • Step 400 The client sends a path calculation request to the server.
  • Step 401 After receiving the path calculation request, the path calculation server performs path calculation according to the constraint condition that does not include the integrated load information of the node, and the obtained path is node 1->node 2->node 4.
  • Step 402 The path calculation server sends a query request to the node 1, the node 2, and the node 4 according to the result of the path calculation.
  • the node 401, the node 1, the node 2, and the node 4 After receiving the query request of the path calculation server, the node 401, the node 1, the node 2, and the node 4 return the current integrated load information to the path calculation server, and assume that the integrated load information of the node 1 is level 1, and the comprehensive load of the node 2 The information is level 5, and the integrated load information of node 4 is level 2.
  • Step 404 The path calculation server determines, according to the integrated load information, that the node 2 is overloaded, does not satisfy the path requirement, and excludes the node 2.
  • Step 405 The path calculation server recalculates the path, and the path information obtained after the recalculation is: Node 1->Node 3 -> Node 4, and the path calculation server queries the Node 1, Node 3, and Node 4 for the integrated load information.
  • Step 406 node 1, node 3, and node 4 return their integrated load information to the path calculation server.
  • the integrated load information of node 1 is level 1
  • the integrated load information of node 3 is level 2
  • the integrated load information of node 4 is At level 2
  • the path calculation server determines that node 1, node 3, and node 4 are not overloaded, meeting the requirements.
  • Step 407 The path calculation server sends the calculated path information to the path calculation client.
  • an embodiment of the present invention further provides a path calculation server, including:
  • the obtaining module 51 is configured to: obtain comprehensive load information of each node in advance;
  • the receiving module 52 is configured to: receive a path calculation request from the client;
  • the calculation module 53 is configured to calculate a path according to the integrated load information of each node.
  • the calculation module 53 is configured to:
  • the path is calculated according to the constraint condition of the integrated load information that does not include the node.
  • the calculation module 53 is configured to:
  • the calculation module 53 is further configured to:
  • the step of calculating the path according to the constraint condition that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded.
  • all or part of the steps of the above embodiments may also be implemented by using an integrated circuit. These steps may be separately fabricated into individual integrated circuit modules, or multiple modules or steps may be fabricated into a single integrated circuit module. achieve.
  • the devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.
  • the device/function module/functional unit in the above embodiment When the device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium.
  • the above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
  • the calculation of the path is performed according to the integrated load information of each node, so that the nodes on the calculated path have sufficient resources for routing processing, thereby improving the success rate of the path calculation.

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)
  • Computer And Data Communications (AREA)

Abstract

A path calculation method and a path calculation server. The method comprises: a path calculation server acquires comprehensive load information of each node in advance (100); and the path calculation server receives a path calculation request from a client, and calculates a path according to the comprehensive load information of each node (101).

Description

一种计算路径的方法和路径计算服务器Method for calculating path and path calculation server 技术领域Technical field
本申请涉及但不限于路由技术。This application relates to, but is not limited to, routing techniques.
背景技术Background technique
路由是指网络中某个节点发现一条或多条到达目的地的路径的过程。路由过程由以下几个部分组成：邻居发现、拓扑发现和路径选择。其中，通过邻居发现，网络中的节点可以发现与它们相邻的邻居节点并且可以了解其自身是如何与这些邻居节点相连的。拓扑发现的作用则是使得节点可以发现网络中的其他节点，并且知道这些节点是如何相连的。得到网络的拓扑信息后，便可以使用路径计算算法来计算从源点到宿点之间的路径。Routing refers to the process by which a node in a network discovers one or more paths to a destination. The routing process consists of the following parts: neighbor discovery, topology discovery, and path selection. Among them, through neighbor discovery, nodes in the network can discover neighbor nodes adjacent to them and can know how they are connected to these neighbor nodes. The role of topology discovery is to enable nodes to discover other nodes in the network and know how these nodes are connected. After obtaining the topology information of the network, the path calculation algorithm can be used to calculate the path from the source point to the sink point.
光网络中的路由需要知道网络中不同资源的类型和限制，在光网络中，资源不可用会导致无法建立连接。在其路由算法中，可以基于一个或多个约束条件计算出所有的可能路径，并根据一定的策略选出一条最优的路径，从而实现网络性能的优化。Routes in an optical network need to know the types and restrictions of different resources in the network. In an optical network, resources are unavailable and connection cannot be established. In its routing algorithm, all possible paths can be calculated based on one or more constraints, and an optimal path is selected according to a certain strategy, thereby optimizing network performance.
发明内容Summary of the invention
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。The following is an overview of the topics detailed in this document. This Summary is not intended to limit the scope of the claims.
在约束条件中，包含了一个“排斥特定网络资源”的约束条件，该约束会根据节点和链路的属性来排除网络中的某些网元用于计算最优路径。但该约束条件仅仅根据链路的状态、节点的可达性等来进行判断，而没有考虑节点自身的实际负荷(如：CPU占用率、内存占用率等)是否超载，在实际的路由过程中，当满足该约束条件的某个节点的实际负荷超载时，会使得业务路由经由该节点时无法得到及时或正确的处理，导致路由失败，从而路径计算的成功率较低。 In the constraint, a constraint of “rejecting specific network resources” is included, which excludes some network elements in the network from being used to calculate the optimal path according to the attributes of the nodes and links. However, the constraint is judged only according to the state of the link, the reachability of the node, etc., and does not consider whether the actual load of the node itself (such as CPU usage, memory usage, etc.) is overloaded, in the actual routing process. When the actual load overload of a node that satisfies the constraint condition causes the service route to be processed in time or correctly through the node, the route fails, and the success rate of the path calculation is low.
本文提出了一种计算路径的方法和路径计算服务器，能够提高路径计算的成功率。This paper proposes a method for calculating paths and a path calculation server, which can improve the success rate of path calculation.
一种计算路径的方法，包括：A method of calculating a path, comprising:
路径计算服务器预先获取每个节点的综合负荷信息；The path calculation server acquires comprehensive load information of each node in advance;
路径计算服务器接收到来自客户端的路径计算请求，根据每个节点的综合负荷信息计算路径。The path calculation server receives the path calculation request from the client, and calculates the path according to the integrated load information of each node.
可选地，所述路径计算服务器根据每个节点的综合负荷信息计算路径包括：Optionally, the path calculation server calculates the path according to the integrated load information of each node, including:
所述路径计算服务器根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径；The path calculation server determines whether each node is overloaded according to the obtained comprehensive load information of each node, and excludes the overloaded node, and calculates the path according to the constraint condition of the integrated load information that does not include the node;
或者，将节点是否超载包含在约束条件中计算路径。Alternatively, include whether the node is overloaded in the constraint to calculate the path.
可选地，所述路径计算服务器根据每个节点的综合负荷信息计算路径包括：Optionally, the path calculation server calculates the path according to the integrated load information of each node, including:
所述路径计算服务器根据不包含节点的综合负荷信息的约束条件计算路径；The path calculation server calculates a path according to a constraint condition that does not include comprehensive load information of the node;
所述路径计算服务器根据计算得到的路径中的每个节点的综合负荷信息判断所述路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。The path calculation server determines whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, sends the calculated path to the client.
可选地，当所述路径计算服务器判断出所述路径中存在超载的节点时，该方法还包括：Optionally, when the path calculation server determines that there is an overloaded node in the path, the method further includes:
排除超载的节点后，继续执行所述根据不包含节点的综合负荷信息的约束条件计算路径的步骤，直到计算得到的路径中的所有节点均不超载。After the overloaded node is excluded, the step of calculating the path according to the constraint that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded.
可选地，所述综合负荷信息为综合负荷值、或所述综合负荷值对应的等级。Optionally, the integrated load information is an integrated load value or a level corresponding to the integrated load value.
可选地，所述综合负荷值根据以下的一个或多个计算：Optionally, the integrated load value is calculated according to one or more of the following:
CPU占用率、等待资源的进程数、内存使用率、吞吐量、中断数。 CPU usage, number of processes waiting for resources, memory usage, throughput, and number of interrupts.
可选地，所述综合负荷值为所述CPU占用率和所述内存使用率之间的加权平均值。Optionally, the integrated load value is a weighted average between the CPU usage and the memory usage.
一种路径计算服务器，包括：A path calculation server, comprising:
获取模块，设置为：预先获取每个节点的综合负荷信息；The obtaining module is set to: obtain comprehensive load information of each node in advance;
接收模块，设置为：接收到来自客户端的路径计算请求；The receiving module is configured to: receive a path calculation request from the client;
计算模块，设置为：根据每个节点的综合负荷信息计算路径。The calculation module is set to: calculate a path according to the integrated load information of each node.
可选地，所述计算模块是设置为：Optionally, the computing module is configured to:
根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径；Judging whether each node is overloaded according to the obtained comprehensive load information of each node, and excluding the overloaded node, calculating the path according to the constraint condition of the integrated load information not including the node;
或者，将节点是否超载包含在约束条件中计算路径。Alternatively, include whether the node is overloaded in the constraint to calculate the path.
可选地，所述计算模块是设置为：Optionally, the computing module is configured to:
根据不包含节点的综合负荷信息的约束条件计算路径；根据计算得到的路径中的每个节点的综合负荷信息判断所述路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。Calculating the path according to the constraint condition of the integrated load information that does not include the node; determining whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, transmitting the calculated path To the client.
一种计算机可读存储介质，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项的方法。A computer readable storage medium storing computer executable instructions for performing the method of any of the above.
本发明实施例包括：路径计算服务器预先获取每个节点的综合负荷信息；路径计算服务器接收到来自客户端的路径计算请求，根据每个节点的综合负荷信息计算路径。通过本发明实施例的方案，根据每个节点的综合负荷信息进行路径的计算，保证了计算得到的路径上的节点有足够的资源进行路由处理，从而提高了路径计算的成功率。The embodiment of the present invention includes: the path calculation server acquires the integrated load information of each node in advance; the path calculation server receives the path calculation request from the client, and calculates the path according to the integrated load information of each node. According to the solution of the embodiment of the present invention, the calculation of the path is performed according to the integrated load information of each node, so that the nodes on the calculated path have sufficient resources for routing processing, thereby improving the success rate of the path calculation.
在阅读并理解了附图和详细描述后，可以明白其他方面。Other aspects will be apparent upon reading and understanding the drawings and detailed description.
附图概述BRIEF abstract
图1为本发明实施例计算路径的方法的流程图；1 is a flowchart of a method for calculating a path according to an embodiment of the present invention;
图2为本发明实施例一个网络的结构组成示意图； 2 is a schematic structural diagram of a network according to an embodiment of the present invention;
图3为本发明实施例网络中每个节点主动上报综合负荷信息时路径计算服务器计算路径的方法的流程图；3 is a flowchart of a method for a path calculation server to calculate a path when each node actively reports comprehensive load information in a network according to an embodiment of the present invention;
图4为本发明实施例路径计算服务器主动查询每个节点的综合负荷信息时路径计算服务器计算路径的方法的流程图；4 is a flowchart of a method for a path calculation server to calculate a path when the path calculation server actively queries the integrated load information of each node according to an embodiment of the present invention;
图5为本发明实施例路径计算服务器的结构组成示意图。FIG. 5 is a schematic structural diagram of a path calculation server according to an embodiment of the present invention.
本发明的实施方式Embodiments of the invention
参见图1，本发明实施例提出了一种计算路径的方法，包括：Referring to FIG. 1, an embodiment of the present invention provides a method for calculating a path, including:
步骤100、路径计算服务器预先获取每个节点的综合负荷信息。Step 100: The path calculation server acquires comprehensive load information of each node in advance.
本步骤中，每个节点可以周期性，或者在接收到来自路径计算服务器的查询请求时计算自身当前的综合负荷信息，并将计算得到的综合负荷信息发送给路径计算服务器；或者，每个节点在判断出自身的综合负荷信息发生变化时将计算得到的综合负荷信息发送给路径计算服务器。In this step, each node may periodically calculate the current integrated load information when receiving the query request from the path calculation server, and send the calculated integrated load information to the path calculation server; or, each node When it is determined that the integrated load information of the self changes, the calculated integrated load information is transmitted to the path calculation server.
其中，综合负荷信息可以是综合负荷值、或综合负荷值对应的等级。The integrated load information may be a comprehensive load value or a level corresponding to the integrated load value.
其中，综合负荷值可以通过与节点的负载相关的指标(如CPU占用率、等待资源的进程数、内存使用率、吞吐量、中断数等)中的一个或多个进行计算，可以采用已有的方法进行计算，这里不再赘述。The integrated load value may be calculated by one or more of the indicators related to the load of the node (such as CPU usage, number of processes waiting for resources, memory usage, throughput, number of interrupts, etc.), and may be used. The method is calculated and will not be described here.
可选地，可以取综合负荷值为CPU占用率和内存使用率之间的加权平均值。Optionally, the combined load value may be a weighted average between the CPU usage and the memory usage.
其中，综合负荷值对应的等级可以根据实际情况进行设定。Among them, the level corresponding to the comprehensive load value can be set according to the actual situation.
步骤101、路径计算服务器接收到来自客户端的路径计算请求，根据每个节点的综合负荷信息计算路径。Step 101: The path calculation server receives a path calculation request from the client, and calculates a path according to the integrated load information of each node.
本步骤包括：This step includes:
路径计算服务器根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径；或者，将节点是否超载包含在约束条件中计算路径。The path calculation server determines whether each node is overloaded according to the obtained comprehensive load information of each node, and excludes the overloaded node, and calculates the path according to the constraint condition of the integrated load information that does not include the node; or, whether the node is overloaded or not included in the constraint condition Calculate the path in .
其中，当综合负荷信息为综合负荷值时，如果节点的综合负荷值大于或 等于预设阈值，则路径计算服务器判断出该节点超载；如果节点的综合负荷值小于预设阈值，则路径计算服务器判断出该节点不超载。Wherein, when the integrated load information is a comprehensive load value, if the integrated load value of the node is greater than or If the threshold is equal to the preset threshold, the path calculation server determines that the node is overloaded; if the integrated load value of the node is less than the preset threshold, the path calculation server determines that the node is not overloaded.
当综合负荷信息为综合负荷值对应的等级时，如果节点的综合负荷值对应的等级大于或等于预设等级，则路径计算服务器判断出该节点超载；如果节点的综合负荷值对应的等级小于预设等级，则路径计算服务器判断出该节点不超载。When the integrated load information is a level corresponding to the integrated load value, if the level corresponding to the integrated load value of the node is greater than or equal to the preset level, the path calculation server determines that the node is overloaded; if the level of the integrated load value of the node is less than the pre- If the level is set, the path calculation server determines that the node is not overloaded.
或者，路径计算服务器根据不包含节点的综合负荷信息的约束条件计算路径；路径计算服务器根据计算得到的路径中的每个节点的综合负荷信息判断路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。如果路径计算服务器判断出路径中存在超载的节点，则排除超载的节点后，继续执行根据不包含节点的综合负荷信息的约束条件计算路径的步骤，直到计算得到的路径中的所有节点均不超载。Alternatively, the path calculation server calculates the path according to the constraint condition that does not include the integrated load information of the node; the path calculation server determines whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, if not, Send the calculated path to the client. If the path calculation server determines that there is an overloaded node in the path, after the overloaded node is excluded, the step of calculating the path according to the constraint condition that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded. .
其中，路径计算服务器根据不包含节点的综合负荷信息的约束条件计算路径后，可以向路径中的每个节点发送查询请求，查询路径中的每个节点的综合负荷信息。After the path calculation server calculates the path according to the constraint condition that does not include the integrated load information of the node, the path request server may send a query request to each node in the path to query the integrated load information of each node in the path.
其中，根据不包含节点的综合负荷信息的约束条件计算路径是指在不考虑网络中每个节点的综合负荷信息的前提下，采用已有的方法来计算路径。将节点是否超载包含在约束条件中计算路径是指将每个节点是否超载作为约束条件之一进行路径计算。Wherein, calculating the path according to the constraint condition of the integrated load information that does not include the node means that the existing method is used to calculate the path without considering the comprehensive load information of each node in the network. Including whether a node is overloaded in a constraint, calculating a path refers to whether each node is overloaded as one of the constraints for path calculation.
图2为一个网络的结构组成示意图，如图2所示，该网络由4个节点以及一个路径计算服务器组成。FIG. 2 is a schematic structural diagram of a network. As shown in FIG. 2, the network is composed of 4 nodes and a path calculation server.
第一实施例，图3为网络中每个节点主动上报综合负荷信息时路径计算服务器计算路径的方法的流程图，如图3所示，该方法包括：In the first embodiment, FIG. 3 is a flowchart of a method for a path calculation server to calculate a path when each node actively reports comprehensive load information in the network. As shown in FIG. 3, the method includes:
步骤300、节点1、节点2、节点3、节点4与路径计算服务器建立连接后，分别向路径计算服务器上报自身初始的综合负荷信息P1、P2、P3、P4。Step 300: Node 1, Node 2, Node 3, and Node 4 establish a connection with the path calculation server, and report their initial integrated load information P1, P2, P3, and P4 to the path calculation server.
本步骤中，综合负荷信息为综合负荷值对应的等级，可以将节点的综合 负荷值分为5个级别进行管理，在计算综合负荷值时只考虑CPU占用率，不考虑内存占用率，则可以确定综合负荷值的1级表示CPU占用率小于或等于20％，2级表示CPU占用率大于20％且小于或等于40％，3级表示CPU占用率大于40％且小于或等于60％，4级表示CPU占用率大于60％且小于或等于80％，5级表示CPU占用率大于80％；In this step, the integrated load information is a level corresponding to the comprehensive load value, and the integration of the nodes can be performed. The load value is divided into five levels for management. When calculating the integrated load value, only the CPU occupancy rate is considered. Regardless of the memory occupancy rate, it can be determined that the level 1 of the integrated load value indicates that the CPU usage is less than or equal to 20%, and the level 2 indicates CPU usage is greater than 20% and less than or equal to 40%. Level 3 indicates that the CPU usage is greater than 40% and less than or equal to 60%. Level 4 indicates that the CPU usage is greater than 60% and less than or equal to 80%. Level 5 indicates CPU usage. The rate is greater than 80%;
假定节点1的初始综合负荷信息P1为3级，节点2的初始综合负荷信息P2为2级，节点3的初始综合负荷信息P3为1级，节点4的初始综合负荷信息P4为2级。It is assumed that the initial integrated load information P1 of the node 1 is 3, the initial integrated load information P2 of the node 2 is 2, the initial integrated load information P3 of the node 3 is 1 level, and the initial integrated load information P4 of the node 4 is 2nd.
步骤301、路径计算服务器接收并保存来自每个节点的综合负荷信息。Step 301: The path calculation server receives and saves the integrated load information from each node.
步骤302、节点1的CPU占用率达到85％时，其综合负荷信息变更为5级，节点1再次向路径计算服务器上报自身的综合负荷信息P1；Step 302: When the CPU usage of the node 1 reaches 85%, the comprehensive load information is changed to level 5, and the node 1 reports its own comprehensive load information P1 to the path calculation server again;
步骤303、路径计算服务器接收到节点1上报的综合负荷信息P1后，更新其本地保存的P1的值。Step 303: After receiving the integrated load information P1 reported by the node 1, the path calculation server updates the value of the locally saved P1.
步骤304、客户端向路径计算服务器发起路径计算请求。Step 304: The client initiates a path calculation request to the path calculation server.
步骤305、路径计算服务器接收到路径计算请求后，获取本地保存的每个节点的综合负荷信息，根据每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点。Step 305: After receiving the path calculation request, the path calculation server acquires the comprehensive load information of each node stored locally, determines whether each node is overloaded according to the comprehensive load information of each node, and excludes the overloaded node.
本步骤中，假定节点1的综合负荷信息为5级，节点2的综合负荷信息为2级，节点3的综合负荷信息为1级，节点4的综合负荷信息为2级。达到5级负荷的节点1已经超载，在计算路径时，把节点1排除在外进行计算。In this step, it is assumed that the integrated load information of the node 1 is 5, the integrated load information of the node 2 is 2, the integrated load information of the node 3 is 1 level, and the integrated load information of the node 4 is 2nd. Node 1 that has reached level 5 load is overloaded. When calculating the path, node 1 is excluded from the calculation.
步骤306、路径计算服务器根据不包含节点的综合负荷信息的约束条件进行路径计算。Step 306: The path calculation server performs path calculation according to a constraint condition that does not include the integrated load information of the node.
步骤307、路径计算服务器将计算得到的路径信息发送给路径计算客户端。Step 307: The path calculation server sends the calculated path information to the path calculation client.
第二实施例，图4为路径计算服务器主动查询每个节点的综合负荷信息时路径计算服务器计算路径的方法的流程图，如图4所示，该方法包括：In the second embodiment, FIG. 4 is a flowchart of a method for a path calculation server to calculate a path when the path calculation server actively queries the integrated load information of each node. As shown in FIG. 4, the method includes:
步骤400、客户端向服务器发送路径计算请求。 Step 400: The client sends a path calculation request to the server.
步骤401、路径计算服务器接收到该路径计算请求后，根据不包含节点的综合负荷信息的约束条件进行路径计算，得到的路径为节点1->节点2->节点4。Step 401: After receiving the path calculation request, the path calculation server performs path calculation according to the constraint condition that does not include the integrated load information of the node, and the obtained path is node 1->node 2->node 4.
步骤402、路径计算服务器根据路径计算的结果，向节点1，节点2，节点4发送查询请求。Step 402: The path calculation server sends a query request to the node 1, the node 2, and the node 4 according to the result of the path calculation.
步骤403、节点1，节点2，节点4接收到路径计算服务器的查询请求后，把自身当前的综合负荷信息返回给路径计算服务器，假定节点1的综合负荷信息为1级，节点2的综合负荷信息为5级，节点4的综合负荷信息为2级。After receiving the query request of the path calculation server, the node 401, the node 1, the node 2, and the node 4 return the current integrated load information to the path calculation server, and assume that the integrated load information of the node 1 is level 1, and the comprehensive load of the node 2 The information is level 5, and the integrated load information of node 4 is level 2.
步骤404、路径计算服务器根据综合负荷信息，判断出节点2的已经超载，不满足路径要求，排除节点2。Step 404: The path calculation server determines, according to the integrated load information, that the node 2 is overloaded, does not satisfy the path requirement, and excludes the node 2.
步骤405、路径计算服务器重新进行路径计算，重新计算后得到的路径信息为：节点1->节点3->节点4，路径计算服务器向节点1，节点3，节点4查询综合负荷信息。Step 405: The path calculation server recalculates the path, and the path information obtained after the recalculation is: Node 1->Node 3 -> Node 4, and the path calculation server queries the Node 1, Node 3, and Node 4 for the integrated load information.
步骤406、节点1，节点3，节点4把自身的综合负荷信息返回给路径计算服务器，节点1的综合负荷信息为1级，节点3的综合负荷信息为2级，节点4的综合负荷信息为2级，路径计算服务器判断出节点1，节点3，节点4均未超载，符合要求。Step 406, node 1, node 3, and node 4 return their integrated load information to the path calculation server. The integrated load information of node 1 is level 1, the integrated load information of node 3 is level 2, and the integrated load information of node 4 is At level 2, the path calculation server determines that node 1, node 3, and node 4 are not overloaded, meeting the requirements.
步骤407、路径计算服务器将计算得到的路径信息发送给路径计算客户端。Step 407: The path calculation server sends the calculated path information to the path calculation client.
参见图5，本发明实施例还提出了一种路径计算服务器，包括：Referring to FIG. 5, an embodiment of the present invention further provides a path calculation server, including:
获取模块51，设置为：预先获取每个节点的综合负荷信息；The obtaining module 51 is configured to: obtain comprehensive load information of each node in advance;
接收模块52，设置为：接收到来自客户端的路径计算请求；The receiving module 52 is configured to: receive a path calculation request from the client;
计算模块53，设置为：根据每个节点的综合负荷信息计算路径。The calculation module 53 is configured to calculate a path according to the integrated load information of each node.
本发明实施例的路径计算服务器中，计算模块53是设置为：In the path calculation server of the embodiment of the present invention, the calculation module 53 is configured to:
根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径。 According to the obtained comprehensive load information of each node, it is judged whether each node is overloaded, and after the overloaded node is excluded, the path is calculated according to the constraint condition of the integrated load information that does not include the node.
本发明实施例的路径计算服务器中，计算模块53是设置为：In the path calculation server of the embodiment of the present invention, the calculation module 53 is configured to:
根据不包含节点的综合负荷信息的约束条件计算路径；根据计算得到的路径中的每个节点的综合负荷信息判断路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。Calculating the path according to the constraint condition of the integrated load information that does not include the node; determining whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, transmitting the calculated path to the client end.
本发明实施例的路径计算服务器中，计算模块53还设置为：In the path calculation server of the embodiment of the present invention, the calculation module 53 is further configured to:
判断出路径中存在超载的节点，排除超载的节点后，继续执行根据不包含节点的综合负荷信息的约束条件计算路径的步骤，直到计算得到的路径中的所有节点均不超载。It is determined that there is an overloaded node in the path, and after the overloaded node is excluded, the step of calculating the path according to the constraint condition that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded.
本领域普通技术人员可以理解上述实施例的全部或部分步骤可以使用计算机程序流程来实现，所述计算机程序可以存储于一计算机可读存储介质中，所述计算机程序在相应的硬件平台上(如***、设备、装置、器件等)执行，在执行时，包括方法实施例的步骤之一或其组合。One of ordinary skill in the art will appreciate that all or a portion of the steps of the above-described embodiments can be implemented using a computer program flow, which can be stored in a computer readable storage medium, such as on a corresponding hardware platform (eg, The system, device, device, device, etc. are executed, and when executed, include one or a combination of the steps of the method embodiments.
可选地，上述实施例的全部或部分步骤也可以使用集成电路来实现，这些步骤可以被分别制作成一个个集成电路模块，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。Alternatively, all or part of the steps of the above embodiments may also be implemented by using an integrated circuit. These steps may be separately fabricated into individual integrated circuit modules, or multiple modules or steps may be fabricated into a single integrated circuit module. achieve.
上述实施例中的装置/功能模块/功能单元可以采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，也可以分布在多个计算装置所组成的网络上。The devices/function modules/functional units in the above embodiments may be implemented by a general-purpose computing device, which may be centralized on a single computing device or distributed over a network of multiple computing devices.
上述实施例中的装置/功能模块/功能单元以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。上述提到的计算机可读取存储介质可以是只读存储器，磁盘或光盘等。When the device/function module/functional unit in the above embodiment is implemented in the form of a software function module and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. The above mentioned computer readable storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
工业实用性Industrial applicability
通过本发明实施例的方案，根据每个节点的综合负荷信息进行路径的计算，保证了计算得到的路径上的节点有足够的资源进行路由处理，从而提高了路径计算的成功率。 According to the solution of the embodiment of the present invention, the calculation of the path is performed according to the integrated load information of each node, so that the nodes on the calculated path have sufficient resources for routing processing, thereby improving the success rate of the path calculation.

Claims (11)

  1. 一种计算路径的方法，包括：A method of calculating a path, comprising:
    路径计算服务器预先获取每个节点的综合负荷信息；The path calculation server acquires comprehensive load information of each node in advance;
    路径计算服务器接收到来自客户端的路径计算请求，根据每个节点的综合负荷信息计算路径。The path calculation server receives the path calculation request from the client, and calculates the path according to the integrated load information of each node.
  2. 根据权利要求1所述的方法，其中，所述路径计算服务器根据每个节点的综合负荷信息计算路径包括：The method of claim 1, wherein the path calculation server calculates the path according to the integrated load information of each node comprises:
    所述路径计算服务器根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径；The path calculation server determines whether each node is overloaded according to the obtained comprehensive load information of each node, and excludes the overloaded node, and calculates the path according to the constraint condition of the integrated load information that does not include the node;
    或者，将节点是否超载包含在约束条件中计算路径。Alternatively, include whether the node is overloaded in the constraint to calculate the path.
  3. 根据权利要求1所述的方法，其中，所述路径计算服务器根据每个节点的综合负荷信息计算路径包括：The method of claim 1, wherein the path calculation server calculates the path according to the integrated load information of each node comprises:
    所述路径计算服务器根据不包含节点的综合负荷信息的约束条件计算路径；The path calculation server calculates a path according to a constraint condition that does not include comprehensive load information of the node;
    所述路径计算服务器根据计算得到的路径中的每个节点的综合负荷信息判断所述路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。The path calculation server determines whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, sends the calculated path to the client.
  4. 根据权利要求3所述的方法，其中，当所述路径计算服务器判断出所述路径中存在超载的节点时，该方法还包括：The method according to claim 3, wherein when the path calculation server determines that there is an overloaded node in the path, the method further includes:
    排除超载的节点后，继续执行所述根据不包含节点的综合负荷信息的约束条件计算路径的步骤，直到计算得到的路径中的所有节点均不超载。After the overloaded node is excluded, the step of calculating the path according to the constraint that does not include the integrated load information of the node is continued until all the nodes in the calculated path are not overloaded.
  5. 根据权利要求1～4任意一项所述的方法，其中，所述综合负荷信息为综合负荷值、或所述综合负荷值对应的等级。The method according to any one of claims 1 to 4, wherein the integrated load information is an integrated load value or a level corresponding to the integrated load value.
  6. 根据权利要求5所述的方法，其中，所述综合负荷值根据以下的一个或多个计算：The method of claim 5 wherein said integrated load value is calculated according to one or more of the following:
    CPU占用率、等待资源的进程数、内存使用率、吞吐量、中断数。 CPU usage, number of processes waiting for resources, memory usage, throughput, and number of interrupts.
  7. 根据权利要求6所述的方法，其中，所述综合负荷值为所述CPU占用率和所述内存使用率之间的加权平均值。The method of claim 6 wherein said integrated load value is a weighted average between said CPU usage and said memory usage.
  8. 一种路径计算服务器，包括：A path calculation server, comprising:
    获取模块，设置为：预先获取每个节点的综合负荷信息；The obtaining module is set to: obtain comprehensive load information of each node in advance;
    接收模块，设置为：接收到来自客户端的路径计算请求；The receiving module is configured to: receive a path calculation request from the client;
    计算模块，设置为：根据每个节点的综合负荷信息计算路径。The calculation module is set to: calculate a path according to the integrated load information of each node.
  9. 根据权利要求8所述的路径计算服务器，其中，所述计算模块是设置为：The path calculation server according to claim 8, wherein said calculation module is configured to:
    根据获得的每个节点的综合负荷信息判断每个节点是否超载，排除超载的节点后，根据不包含节点的综合负荷信息的约束条件计算路径；Judging whether each node is overloaded according to the obtained comprehensive load information of each node, and excluding the overloaded node, calculating the path according to the constraint condition of the integrated load information not including the node;
    或者，将节点是否超载包含在约束条件中计算路径。Alternatively, include whether the node is overloaded in the constraint to calculate the path.
  10. 根据权利要求8所述的路径计算服务器，其中，所述计算模块是设置为：The path calculation server according to claim 8, wherein said calculation module is configured to:
    根据不包含节点的综合负荷信息的约束条件计算路径；根据计算得到的路径中的每个节点的综合负荷信息判断所述路径中是否存在超载的节点，如果不存在，则将计算得到的路径发送给客户端。Calculating the path according to the constraint condition of the integrated load information that does not include the node; determining whether there is an overloaded node in the path according to the integrated load information of each node in the calculated path, and if not, transmitting the calculated path To the client.
  11. 一种计算机可读存储介质，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权利要求1-7任一项的方法。 A computer readable storage medium storing computer executable instructions for performing the method of any of claims 1-7.
PCT/CN2015/088044 2014-11-18 2015-08-25 Path calculation method and path calculation server WO2016078461A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410657336.5 2014-11-18
CN201410657336.5A CN105591888A (en) 2014-11-18 2014-11-18 Route-computing method and server

Publications (1)

Publication Number Publication Date
WO2016078461A1 true WO2016078461A1 (en) 2016-05-26

Family

ID=55931133

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/088044 WO2016078461A1 (en) 2014-11-18 2015-08-25 Path calculation method and path calculation server

Country Status (2)

Country Link
CN (1) CN105591888A (en)
WO (1) WO2016078461A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6427697B1 (en) * 2018-01-22 2018-11-21 株式会社Ｔｒｉａｒｔ INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, PROGRAM, AND INFORMATION PROCESSING SYSTEM

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1860748A (en) * 2004-03-18 2006-11-08 松下电器产业株式会社 Radio communication device and route search method
US20080151896A1 (en) * 2005-05-20 2008-06-26 Renhai Zhang Method and Apparatus for Computing a Path in a Network Domain
CN101312464A (en) * 2008-07-11 2008-11-26 烽火通信科技股份有限公司 Method for realizing load balance in automatic exchange optical network
CN102594449A (en) * 2012-02-14 2012-07-18 中兴通讯股份有限公司 Implementation system and method of multipath calculating element cooperation in optical networks
CN103188149A (en) * 2011-12-28 2013-07-03 ***通信集团广东有限公司 Routing computation method and router

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102136994B (en) * 2010-08-02 2014-04-30 华为技术有限公司 Label switched path creation method, system and node equipment
CN102055675B (en) * 2011-01-21 2012-12-19 清华大学 Multipath routing distribution method based on load equilibrium
EP2754272B1 (en) * 2011-09-09 2018-03-21 Nokia Solutions and Networks Oy Method, device and system for providing and selecting candidate nodes for live streaming services
CN103716251B (en) * 2014-01-14 2017-06-27 三星电子（中国）研发中心 For the load-balancing method and equipment of content distributing network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1860748A (en) * 2004-03-18 2006-11-08 松下电器产业株式会社 Radio communication device and route search method
US20080151896A1 (en) * 2005-05-20 2008-06-26 Renhai Zhang Method and Apparatus for Computing a Path in a Network Domain
CN101312464A (en) * 2008-07-11 2008-11-26 烽火通信科技股份有限公司 Method for realizing load balance in automatic exchange optical network
CN103188149A (en) * 2011-12-28 2013-07-03 ***通信集团广东有限公司 Routing computation method and router
CN102594449A (en) * 2012-02-14 2012-07-18 中兴通讯股份有限公司 Implementation system and method of multipath calculating element cooperation in optical networks

Also Published As

Publication number Publication date
CN105591888A (en) 2016-05-18

Similar Documents

Publication Publication Date Title
US9634923B2 (en) Method, apparatus and system for disseminating routing information
US8773992B2 (en) Methods and apparatus for hierarchical routing in communication networks
US8995277B2 (en) Method for dynamic load balancing of network flows on LAG interfaces
US9548927B2 (en) Flow-based load balancing
JP5276220B2 (en) Bus control device and control device for outputting instructions to bus control device
JP4951717B2 (en) How to select backup resources, system
US20070110063A1 (en) Apparatus, system, and method for reliable, fast, and scalable multicast message delivery in service overlay networks
US9853906B2 (en) Network prioritization based on node-level attributes
WO2016091029A1 (en) Method and apparatus for forwarding traffic of stacking system
US20160065449A1 (en) Bandwidth-Weighted Equal Cost Multi-Path Routing
JP5884892B2 (en) Network system, controller, and load balancing method
JP6256343B2 (en) Network, network node, distribution method, and network node program
CN104283807A (en) TE tunnel building method and device
US8908565B2 (en) Methods and apparatus for efficient decentralized information dissemination in a network
US11277342B2 (en) Lossless data traffic deadlock management system
JPWO2010092751A1 (en) Event distribution system, rendezvous node, broker node, load distribution method for event distribution system, load distribution method for rendezvous node, distribution route construction method for broker node, load distribution program, and distribution route construction program
WO2010101038A1 (en) Destination node selection method, node, and recording medium
EP3063969B1 (en) System and method for traffic engineering using link buffer status
WO2016078461A1 (en) Path calculation method and path calculation server
JP2015130551A (en) network design method and system
WO2020261393A1 (en) Communication device and communication method
US20140019508A1 (en) Distributed processing system, distributed processing device, routing table creation method and program recording medium
US10158546B2 (en) System and method for power reduction in network equipment
JP2009033345A (en) Multi-hop network system
KR101440454B1 (en) Apparatus and method of flow routing considering available bandwidth in WLAN mesh 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: 15860112

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: 15860112

Country of ref document: EP

Kind code of ref document: A1