公开(公告)号：US20130051223A1

公开(公告)日：2013-02-28

申请号：US13508758

申请日：2010-08-18

申请人： János Farkas

发明人： János Farkas

IPC分类号： H04L12/24

CPC分类号： H04L45/28 ,  H04L12/462 ,  H04L12/4625 ,  H04L41/0803 ,  H04L45/021 ,  H04L45/48 ,  H04L45/66 ,  H04L45/72

摘要： A system (300), a network management system (306), and a method are described herein for avoiding a count-to-infinity problem in a network (304)(e.g., Provider Backbone Bridging) with bridges having network interface ports (2,4,)(e,g., Layer Two Gateway Ports) which are connected to an external network (302)(e.g., External Network to Network interface).

摘要翻译： 这里描述了一种系统（300），网络管理系统（306）和方法，用于避免具有网络接口端口（2）的网络（304）（例如，提供商骨干桥接）中的无穷大计数问题 ，例如，外部网络到网络接口）连接到外部网络（302），例如，第二层网关端口（例如，二层网关端口）。

公开(公告)号：US20120281524A1

公开(公告)日：2012-11-08

申请号：US13394446

申请日：2009-10-02

申请人： János Farkas

发明人： János Farkas

IPC分类号： H04L29/14 ,  H04L12/26

CPC分类号： H04L45/00 ,  H04L43/0817 ,  H04L45/24 ,  H04L45/28 ,  H04L45/48 ,  H04L45/66

摘要： Technique for controlling data forwarding in a computer network are provided. The network comprises a set of nodes for forwarding data, wherein a first node is associated with a primary tree and a backup tree, wherein the primary tree defines a default path for the first node to forward data to a second node and the backup tree defines another path for the data forwarding in case of a failure of the primary tree. The basic principle of the techniques is to notify the first node of a failure of the primary tree wherein the notification is provided by the second node. The techniques are particularly beneficial for computer networks offering multipoint services, such as SPB-controlled networks, because the techniques ensure the congruency of the forward and reverse paths even when the data forwarding has been switched from the primary tree to the backup tree.

摘要翻译： 提供了一种用于控制计算机网络中数据转发的技术。 网络包括用于转发数据的一组节点，其中第一节点与主树和备份树相关联，其中主树定义用于第一节点将数据转发到第二节点的默认路径，并且备份树定义 在主树失败的情况下数据转发的另一路径。 该技术的基本原理是向第一节点通知主树的故障，其中通知由第二节点提供。 这些技术对于提供多点服务（例如SPB控制网络）的计算机网络特别有利，因为即使当数据转发已经从主树切换到备份树时，这些技术确保前向和反向路径的一致性。

公开(公告)号：US08014320B2

公开(公告)日：2011-09-06

申请号：US12519792

申请日：2007-10-09

申请人： János Farkas ,  Vinicius Garcia de Oliveira ,  Marcos Rogério Salvador

发明人： János Farkas ,  Vinicius Garcia de Oliveira ,  Marcos Rogério Salvador

IPC分类号： H04L12/44

CPC分类号： H04L41/0806 ,  H04L12/4641 ,  H04L41/0213 ,  H04L41/12

摘要： A method and arrangement for discovering the physical topology of a telecommunication network having switches, routers, and a management node interconnected by links in a spanning tree and links to blocked interfaces. The management node broadcasts a ping message and adds replying nodes to the topology. The management node discovers the spanning tree by retrieving address forwarding tables from the switches, assigning them a ranking value, and connecting from the highest ranked nodes to successively lower ranked nodes. The management node discovers the blocked interfaces by configuring a VLAN to include the spanning tree and disabling the spanning tree protocol. The blocked interfaces are turned on and off while matching link down traps are noted and the corresponding links are discovered. Only basic management features of the switches are needed, and all nodes and links are discovered.

摘要翻译： 一种用于发现具有交换机，路由器和管理节点的电信网络的物理拓扑的方法和装置，所述交换机，路由器和管理节点通过生成树中的链路和阻塞接口的链路相互连接。 管理节点广播ping消息，并将回复节点添加到拓扑。 管理节点通过从交换机检索地址转发表，分配排序值，从最高排名的节点到连续降低排名的节点进行连接，发现生成树。 管理节点通过配置VLAN包括生成树和禁用生成树协议来发现阻塞的接口。 阻塞的接口被打开和关闭，而匹配的链路陷阱被注意到并且相应的链接被发现。 只需要交换机的基本管理功能，并发现所有节点和链路。

公开(公告)号：US20100020722A1

公开(公告)日：2010-01-28

申请号：US12519792

申请日：2007-10-09

申请人： János Farkas ,  Vinicius Garcia de Oliveira ,  Marcos Rogério Salvador

发明人： János Farkas ,  Vinicius Garcia de Oliveira ,  Marcos Rogério Salvador

IPC分类号： H04L12/28

CPC分类号： H04L41/0806 ,  H04L12/4641 ,  H04L41/0213 ,  H04L41/12

摘要： A network (NW1) has switches (S1-S7), routers (R1-R4) and a management node (NMS1) interconnected by links (PL1) in a spanning tree (ST1) and links (PL2) to blocked interfaces. Switches and routers have the IP address of the management node. The nodes are discovered by the management node (NMS1) broadcasting a ping message (PiI) and on reply (RPiI) adds the nodes to the topology. The spanning tree (ST1) is discovered in that the management node retrieves address forwarding tables from the switches and assigns them a ranking value. From the highest ranked node successively lower ranked nodes are connected. The blocked interfaces (PL2) are discovered by configuring a VLAN (VLANI) to include only the spanning tree (ST1) and disabling the latter The blocked interfaces are turned off and on, matching link down traps are noted and the corresponding link (PL2) is discovered. The status of the interfaces (1, 2, 3 . . . ) are cyclically checked for changes and new links and network segments are added. Only basic management features of the switches are needed and all nodes and links are discovered.

摘要翻译： 网络（NW1）具有通过生成树（ST1）中的链路（PL1）和链路（PL2）与阻塞接口互连的交换机（S1-S7），路由器（R1-R4）和管理节点（NMS1）。 交换机和路由器具有管理节点的IP地址。 节点被广播ping消息（PiI）的管理节点（NMS1）发现，并且响应（RPiI）将节点添加到拓扑。 发现生成树（ST1），管理节点从交换机检索地址转发表，并为它们分配排序值。 从排名最高的节点连续下降的节点连接起来。 通过配置VLAN（VLANI）仅包括生成树（ST1）并禁用后者阻塞接口（PL2）被发现阻塞接口关闭和打开，匹配链路陷阱陷阱和对应链路（PL2） 被发现。 循环检查接口（1，2，3 ...）的状态，并添加新的链接和网段。 只需要交换机的基本管理功能，并发现所有节点和链路。

公开(公告)号：US08923164B2

公开(公告)日：2014-12-30

申请号：US13143593

申请日：2011-06-28

申请人： János Farkas ,  David Ian Allan ,  Scott Mansfield

发明人： János Farkas ,  David Ian Allan ,  Scott Mansfield

IPC分类号： H04L12/28 ,  H04L12/753 ,  H04L12/46 ,  H04L12/721

CPC分类号： H04L45/48 ,  H04L12/4625 ,  H04L45/12 ,  H04L47/125

摘要： A node and a method are described herein for computing forwarding trees to distribute traffic in a network. In addition, a network is described herein that has a plurality of nodes interconnected to one another by a plurality of network links, and each node is configured to perform multiple rounds of forwarding tree computations to distribute traffic load on one or more of the network links to the other nodes.

摘要翻译： 本文描述了用于计算转发树以在网络中分发业务的节点和方法。 此外，这里描述了具有通过多个网络链路彼此互连的多个节点的网络，并且每个节点被配置为执行多轮转发树计算以在一个或多个网络链路上分配业务负载 到其他节点。

公开(公告)号：US08923112B2

公开(公告)日：2014-12-30

申请号：US13394446

申请日：2009-10-02

申请人： János Farkas

发明人： János Farkas

IPC分类号： G01R31/08 ,  G06F11/00 ,  G08C15/00 ,  H04J1/16 ,  H04J3/14 ,  H04L1/00 ,  H04L12/26 ,  G06F15/173 ,  H04L12/701 ,  H04L12/707 ,  H04L12/703 ,  H04L12/753 ,  H04L12/721

CPC分类号： H04L45/00 ,  H04L43/0817 ,  H04L45/24 ,  H04L45/28 ,  H04L45/48 ,  H04L45/66

摘要： Technique for controlling data forwarding in a computer network are provided. The network comprises a set of nodes for forwarding data, wherein a first node is associated with a primary tree and a backup tree, wherein the primary tree defines a default path for the first node to forward data to a second node and the backup tree defines another path for the data forwarding in case of a failure of the primary tree. The basic principle of the techniques is to notify the first node of a failure of the primary tree wherein the notification is provided by the second node. The techniques are particularly beneficial for computer networks offering multipoint services, such as SPB-controlled networks, because the techniques ensure the congruency of the forward and reverse paths even when the data forwarding has been switched from the primary tree to the backup tree.

摘要翻译： 提供了一种用于控制计算机网络中数据转发的技术。 网络包括用于转发数据的一组节点，其中第一节点与主树和备份树相关联，其中主树定义用于第一节点将数据转发到第二节点的默认路径，并且备份树定义 在主树失败的情况下数据转发的另一路径。 该技术的基本原理是向第一节点通知主树的故障，其中通知由第二节点提供。 这些技术对于提供多点服务（例如SPB控制网络）的计算机网络特别有利，因为即使当数据转发已经从主树切换到备份树时，这些技术确保前向和反向路径的一致性。

公开(公告)号：US08699380B2

公开(公告)日：2014-04-15

申请号：US13146803

申请日：2009-01-30

申请人： Gábor Kapitany ,  Sándor Plosz ,  Dániel Horvath ,  Richard Pallos ,  János Farkas

发明人： Gábor Kapitany ,  Sándor Plosz ,  Dániel Horvath ,  Richard Pallos ,  János Farkas

IPC分类号： H04L12/28

CPC分类号： H04L12/437 ,  H04L12/462 ,  H04L45/02 ,  H04L45/025 ,  H04L45/18 ,  H04L45/28 ,  H04L45/48 ,  H04L45/66 ,  Y02D30/32

摘要： A method and apparatus for flushing port tables in an Ethernet network that includes a Root Bridge node (1) and a plurality of bridge nodes (2-7). A ring of bridge nodes affected by a change in the topology of the Ethernet network is identified from the plurality of, bridge nodes. The ring of bridge nodes (2-7) includes a branching bridge node (2) providing a connection to the Root Bridge node (1). Port tables are flushed only at the bridge nodes on the ring (2-7), rather than all of the bridge nodes in the Ethernet network, which greatly reduces the amount of signalling required during a relearning process.

摘要翻译： 一种用于冲洗包括根网桥节点（1）和多个网桥节点（2-7）的以太网网络中的端口表的方法和装置。 从多个桥节点识别受以太网网络拓扑变化影响的网桥节点环。 桥节点（2-7）环包括提供到根网桥节点（1）的连接的分支桥节点（2）。 端口表仅在环（2-7）的桥节点刷新，而不是以太网中的所有网桥节点，这大大减少了重新学习过程中所需的信号量。

公开(公告)号：US20120120803A1

公开(公告)日：2012-05-17

申请号：US13143593

申请日：2011-06-28

申请人： János Farkas ,  David Ian Allan ,  Scott Mansfield

发明人： János Farkas ,  David Ian Allan ,  Scott Mansfield

IPC分类号： H04L12/26

CPC分类号： H04L45/48 ,  H04L12/4625 ,  H04L45/12 ,  H04L47/125

摘要： A node and a method are described herein for computing forwarding trees to distribute traffic in a network. In addition, a network is described herein that has a plurality of nodes interconnected to one another by a plurality of network links, and each node is configured to perform multiple rounds of forwarding tree computations to distribute traffic load on one or more of the network links to the other nodes.

摘要翻译： 本文描述了用于计算转发树以在网络中分发业务的节点和方法。 此外，这里描述了具有通过多个网络链路彼此互连的多个节点的网络，并且每个节点被配置为执行多轮转发树计算以在一个或多个网络链路上分配业务负载 到其他节点。

公开(公告)号：US20120106322A1

公开(公告)日：2012-05-03

申请号：US13181020

申请日：2011-07-12

申请人： Balázs Peter Gero ,  János Farkas ,  Panagiotis Saltsidis ,  Zhemin Ding

发明人： Balázs Peter Gero ,  János Farkas ,  Panagiotis Saltsidis ,  Zhemin Ding

IPC分类号： H04L12/26

CPC分类号： H04L45/28 ,  H04L12/437 ,  H04L45/04 ,  H04L45/22 ,  H04L45/24 ,  H04L45/58

摘要： A method and network for determining an interconnect node for establishing a forwarding path for service based data within a network system. The method includes assigning, interconnect node status information to network interconnect nodes, wherein a network interconnect node to which a passive status is assigned is only allowed to transmit service based data between an external link and another interconnect node of the network, or between two other interconnect nodes of the network. Only a network interconnect node with active status is allowed to send or receive service based data to or from the network. The method includes determining, for a given service, an interconnect node with active status for establishment of a forwarding path including the interconnect node with active status and an external link, wherein the determination is based on the respective status information assigned to the network interconnect nodes for the service.

摘要翻译： 一种用于确定互连节点的方法和网络，用于在网络系统内建立用于基于服务的数据的转发路径。 该方法包括将节点状态信息分配给网络互连节点，其中分配了被动状态的网络互连节点仅被允许在网络的外部链路和另一互连节点之间或另外两个之间传输基于服务的数据 网络的互连节点。 仅允许具有活动状态的网络互连节点向网络发送或接收基于服务的数据。 该方法包括为给定服务确定具有活动状态的互连节点，用于建立包括具有活动状态的互连节点和外部链路的转发路径，其中所述确定基于分配给网络互连节点的相应状态信息 为服务。

公开(公告)号：US20110022725A1

公开(公告)日：2011-01-27

申请号：US12922235

申请日：2009-03-10

申请人： János Farkas

发明人： János Farkas

IPC分类号： G06F15/173

CPC分类号： H04L45/14 ,  H04L45/00 ,  H04L45/02 ,  H04L45/021 ,  H04L45/023 ,  H04L45/123 ,  H04L45/18

摘要： A network node of a telecommunications network controlled by a link-state protocol includes a network interface which receives a message that contains information on a change in topology of the network. The node includes a processing unit that blocks forwarding of traffic to at least one neighbor node of the network at the network interface, agrees on the change in topology with the neighbor node; and unblocks the forwarding of traffic when the neighbor node has information about the topology which is the same as the information about the topology in a memory. A transient loop prevention method of a network node of a network having a plurality of a network nodes controlled by a link-state protocol includes the steps of receiving a message at a network interface which contains information on a change in topology of the network. There is the step of blocking forwarding of traffic to each neighbor node of the network at the network interface by a processing unit. There is the step of agreeing by the processing unit on the change in topology with the neighbor node. There is the step of unblocking the forwarding of traffic when the neighbor node has information about the topology which is the same as the information about the topology stored in a memory.

摘要翻译： 由链路状态协议控制的电信网络的网络节点包括接收包含关于网络拓扑变化的信息的消息的网络接口。 该节点包括一个处理单元，其阻止在网络接口处向网络的至少一个相邻节点转发流量，与邻居节点的拓扑变化一致; 并且当相邻节点具有关于与存储器中的拓扑的信息相同的拓扑的信息时，解除阻塞流量的转发。 具有由链路状态协议控制的多个网络节点的网络的网络节点的暂态环路防止方法包括以下步骤：在包含关于网络拓扑变化的信息的网络接口处接收消息。 通过处理单元在网络接口处阻塞流量到网络的每个邻居节点的步骤。 处理单元同邻近节点拓扑变化的步骤。 当邻居节点具有关于与存储在存储器中的拓扑的信息相同的拓扑的信息时，解除阻塞流量的转发的步骤。