-
21.发明申请公开(公告)号：US20060159083A1
公开(公告)日：2006-07-20
申请号：US11040629
申请日：2005-01-19
IPC分类号： H04L12/28
摘要： A method and apparatus for the dissemination of non-routing information to nodes of a network is provided. A new type of IS-IS packet (called a NRI IS-IS packet) is described that exclusively carries non-routing information. When the NRI IS-IS packet is received by a router, the router may send the NRI IS-IS packet to an appropriate component responsible for processing non-routing information, without analyzing, verifying, and validating the information carried in each TLV and sub-TLV of the NRI IS-IS packet. Advantageously, the time it takes for routers of the network to achieve convergence is decreased since a IS-IS packet reader need not analyze, verify, and validate information not related to network topology and IP routing. Therefore, when NRI IS-IS packets are received, there is no impact in the convergence time of nodes in the network.
摘要翻译： 提供了一种用于将非路由信息传播到网络节点的方法和装置。 描述了一种新型的IS-IS分组（称为NRI IS-IS分组），其独有地携带非路由信息。 当路由器接收到NRI IS-IS报文时，路由器可以将NRI IS-IS报文发送给负责处理非路由信息的适当组件，而无需分析，验证和验证每个TLV和Sub -TLV的NRI IS-IS包。 有利的是，由于IS-IS分组读取器不需要分析，验证和验证与网络拓扑和IP路由不相关的信息，所以网络路由器实现收敛所需的时间被减少。 因此，当收到NRI IS-IS报文时，网络节点的收敛时间不会有任何影响。
-
公开(公告)号：US20060013125A1
公开(公告)日：2006-01-19
申请号：US10891704
申请日：2004-07-15
IPC分类号： H04L12/26
摘要： A technique treats a protected forwarding adjacency (FA) as a dynamic entity in that it allows a backup tunnel associated with the FA to carry traffic for the FA, when it's primary tunnel has failed, up to a predetermined amount of time. If after the predetermined amount of time has elapsed and the FA has not recovered (e.g., the primary tunnel has not been reestablished), a network topology change is automatically triggered causing the network to converge on a new network topology. By triggering the network topology change, a path that is more optimal than the path associated with the backup tunnel may be subsequently determined to carry the traffic.
摘要翻译： 一种技术将受保护的转发邻接（FA）视为动态实体，因为当主隧道发生故障时，它允许与FA相关联的备用隧道携带FA的流量，直到预定的时间量。 如果经过了预定的时间量并且FA没有恢复（例如，主隧道没有被重新建立），则自动地触发网络拓扑变化，导致网络收敛在新的网络拓扑上。 通过触发网络拓扑变化，可以随后确定比与备用隧道相关联的路径更优化的路径来承载流量。
-
公开(公告)号：US09300564B2
公开(公告)日：2016-03-29
申请号：US13524057
申请日：2012-06-15
IPC分类号： H04L12/26 , H04L12/24 , H04L12/751 , H04L12/703 , H04L12/717 , H04L12/723
摘要： In one embodiment, a stateful path computation element (PCE) in a computer network determines a need to route at least a threshold number of tunnels, and in response, triggers a routing update from a determined set of routers. Having updated the routing information and available network resources for the set of routers, the stateful PCE may then compute the tunnels based on the update.
摘要翻译： 在一个实施例中，计算机网络中的有状态路径计算元件（PCE）确定需要路由至少一个阈值数量的隧道，并且作为响应，从确定的一组路由器触发路由更新。 为了更新路由器集合的路由信息和可用的网络资源，状态PCE然后可以基于更新来计算隧道。
-
24.发明授权Global state resynchronization for path computation element failure during a reoptimization process 有权重新优化过程中路径计算元素故障的全局状态重新同步公开(公告)号：US09077615B2
公开(公告)日：2015-07-07
申请号：US13524632
申请日：2012-06-15
IPC分类号： H04L1/02 , H04J3/14 , H04L12/24 , H04L12/46 , H04L12/751 , H04L12/707 , H04L12/703 , H04L12/717 , H04L12/723 , H04L12/26
CPC分类号： H04L41/0663 , H04L12/4633 , H04L43/10 , H04L45/02 , H04L45/22 , H04L45/28 , H04L45/42 , H04L45/50
摘要： In one embodiment, a router initiates reroutes of one or more tunnels at the router as part of optimization of a plurality of tunnels in a computer network, and stores an original state of the one or more tunnels at the router prior to the optimization. By detecting whether path computation element (PCE) failure occurs prior to completion of the optimization, the router may revert to the original state of the one or more tunnels in response to PCE failure prior to completion of the optimization.
摘要翻译： 在一个实施例中，路由器发起路由器处的一个或多个隧道的路由器作为计算机网络中的多个隧道的优化的一部分，并且在优化之前在路由器处存储一个或多个隧道的原始状态。 通过检测在优化完成之前是否发生路径计算元件（PCE）故障，路由器可以在完成优化之前响应于PCE故障而恢复到一个或多个隧道的原始状态。
-
公开(公告)号：US20130336159A1
公开(公告)日：2013-12-19
申请号：US13524071
申请日：2012-06-15
申请人： Stefano Previdi , Jean-Philippe Vasseur , Jan Medved , David Ward
发明人： Stefano Previdi , Jean-Philippe Vasseur , Jan Medved , David Ward
IPC分类号： H04L12/28
摘要： In one embodiment, a particular device in a computer network maintains a locally owned tunnel-state table, and joins a distributed hash table (DHT) ring. In addition, the locally owned tunnel-state table is shared with other devices of the DHT ring to establish a DHT-owned tunnel-state table. The particular device (and other devices) determines ownership of link-state advertisements (LSAs) for a specific portion of a traffic engineering database (TED) according to the DHT ring. As such, when the particular device (or any device) computes a path for a tunnel using a local TED, the particular device may request permission to use resources along the computed path that were advertised in particular LSAs from owners of those particular LSAs when not owned by the particular device.
摘要翻译： 在一个实施例中，计算机网络中的特定设备维护本地拥有的隧道状态表，并且连接分布式散列表（DHT）环。 此外，本地拥有的隧道状态表与DHT环的其他设备共享，以建立DHT拥有的隧道状态表。 特定设备（和其他设备）根据DHT环确定针对流量工程数据库（TED）的特定部分的链路状态通告（LSA）的所有权。 因此，当特定设备（或任何设备）使用本地TED计算隧道的路径时，特定设备可以请求允许沿着所计算的路径使用资源，这些资源在特定LSA的特定LSA中被从该特定LSA的所有者通告 由特定设备拥有。
-
公开(公告)号：US20130336109A1
公开(公告)日：2013-12-19
申请号：US13524057
申请日：2012-06-15
摘要： In one embodiment, a stateful path computation element (PCE) in a computer network determines a need to route at least a threshold number of tunnels, and in response, triggers a routing update from a determined set of routers. Having updated the routing information and available network resources for the set of routers, the stateful PCE may then compute the tunnels based on the update.
摘要翻译： 在一个实施例中，计算机网络中的有状态路径计算元件（PCE）确定需要路由至少一个阈值数量的隧道，并且作为响应，从确定的一组路由器触发路由更新。 为了更新路由器集合的路由信息和可用的网络资源，状态PCE然后可以基于更新来计算隧道。
-
27.发明申请公开(公告)号：US20130336108A1
公开(公告)日：2013-12-19
申请号：US13524632
申请日：2012-06-15
IPC分类号： H04L12/26
CPC分类号： H04L41/0663 , H04L12/4633 , H04L43/10 , H04L45/02 , H04L45/22 , H04L45/28 , H04L45/42 , H04L45/50
摘要： In one embodiment, a router initiates reroutes of one or more tunnels at the router as part of optimization of a plurality of tunnels in a computer network, and stores an original state of the one or more tunnels at the router prior to the optimization. By detecting whether path computation element (PCE) failure occurs prior to completion of the optimization, the router may revert to the original state of the one or more tunnels in response to PCE failure prior to completion of the optimization.
摘要翻译： 在一个实施例中，路由器发起路由器处的一个或多个隧道的路由器作为计算机网络中的多个隧道的优化的一部分，并且在优化之前在路由器处存储一个或多个隧道的原始状态。 通过检测在优化完成之前是否发生路径计算元件（PCE）故障，路由器可以在完成优化之前响应于PCE故障而恢复到一个或多个隧道的原始状态。
-
公开(公告)号：US20060176820A1
公开(公告)日：2006-08-10
申请号：US11052280
申请日：2005-02-07
摘要： A technique triggers optimization of a traffic engineering (TE) label switched path (LSP) that spans multiple domains of a computer network from a head-end node of a local domain to a tail-end node of a remote domain. The technique is based on the detection of an event in the remote domain (“event domain”) that could create a more optimal TE-LSP, such as, e.g., restoration of a network element or increased available bandwidth. Specifically, a path computation element (PCE) in the event domain learns of the event and notifies other PCEs of the event through an event notification. These PCEs then flood an event notification to label switched routers (LSRs) in their respective domain. Upon receiving the notification, if an LSR has one or more TE-LSPs (or pending TE-LSPs), it responds to the PCE with an optimization request for the TE-LSPs. The PCE determines whether a particular TE-LSP may benefit from optimization based on the event domain (i.e., whether the TE-LSP uses the event domain), and processes the request accordingly.
摘要翻译： 一种技术触发跨越计算机网络的多个域从本地域的头端节点到远程域的尾端节点的流量工程（TE）标签交换路径（LSP）的优化。 该技术基于对远程域（“事件域”）中的事件的检测，其可以创建更优化的TE-LSP，例如网络元件的恢复或增加的可用带宽。 具体地，事件域中的路径计算元素（PCE）学习事件并通过事件通知通知其他PCE事件。 然后，这些PCE将事件通知泛滥到其各自域中的标签交换路由器（LSR）。 在收到通知后，如果LSR有一个或多个TE-LSP（或待处理的TE-LSP），则对该TEE的优先请求响应PCE。 PCE确定特定TE-LSP是否可以从基于事件域的优化（即，TE-LSP是否使用事件域）获益，并且相应地处理该请求。
-
公开(公告)号：US20060171331A1
公开(公告)日：2006-08-03
申请号：US11048077
申请日：2005-02-01
CPC分类号： H04L45/026 , H04L43/0811 , H04L45/26 , H04L45/28 , H04L63/0272
摘要： Customer edge (CE) to CE device verification checks initiate routes from available CEs as a set of path verification messages, destined for remote CE routes serving a remote VPN. An extended community attribute, included among the attributes of the path verification message, stores the identity of the originating CE router. The path verification message propagates across the network, and transports the identity of the originating CE router because the originator identity is not overwritten by successive routing. Upon receipt by the remote CE, the originator is determinable from the extended community attribute. A further reachability field is also included in the extended community attribute and indicates whether per CE or per prefix is appropriate for the particular route in question. In this manner, CE-CE connectivity checks identify CEs which are reachable from other CEs. Accordingly, such a mechanism allows for route reachability aggregation on a per-CE or per-prefix reachability basis.
摘要翻译： 客户端（CE）到CE设备验证检查从可用的CE启动路由作为一组路径验证消息，目的地是服务于远程VPN的远程CE路由。 包含在路径验证消息的属性之间的扩展团体属性存储始发CE路由器的身份。 路径验证消息通过网络传播，并传输始发CE路由器的身份，因为始发方身份不会被连续路由覆盖。 远程CE收到后，发起者可以从扩展团体属性中确定。 扩展社区属性中还包括另外的可访问性字段，并指示每个CE或每个前缀是否适合所讨论的特定路由。 以这种方式，CE-CE连接检查可以识别可从其他CE接入的CE。 因此，这种机制允许基于每个CE或每个前缀可达性的路由可达性聚合。
-
公开(公告)号：US07747777B2
公开(公告)日：2010-06-29
申请号：US11948799
申请日：2007-11-30
IPC分类号： G06F15/173
摘要： In one embodiment, an apparatus comprises logic for optimizing network resources usage. The logic is operable to store IGP information, where the IGP information includes a set of attribute values associated with each of a set of content servers. When the logic receives a request for content from a remote peer, the logic determines one or more content servers that can provide the requested content. The logic then retrieves, from the IGP information, a plurality of attribute values associated with a non-looping path from each of the one or more content servers. For each of the one or more content servers, the retrieved attribute values include: one or more capacity values indicating capacities of one or more communication links on the non-looping path from that content server; and one or more utilization values indicating utilizations of the one or more communication links on the non-looping path from that content server. The logic then selects a content server based on the retrieved attribute values, and causes the request for the content to be sent to the selected content server.
摘要翻译： 在一个实施例中，一种装置包括用于优化网络资源使用的逻辑。 逻辑可操作地存储IGP信息，其中IGP信息包括与一组内容服务器中的每一个相关联的一组属性值。 当逻辑从远程对等体接收到对内容的请求时，逻辑确定可以提供所请求的内容的一个或多个内容服务器。 然后，逻辑从IGP信息中检索与一个或多个内容服务器中的每一个的非循环路径相关联的多个属性值。 对于所述一个或多个内容服务器中的每一个，所检索的属性值包括：指示来自该内容服务器的非循环路径上的一个或多个通信链路的容量的一个或多个容量值; 以及指示来自该内容服务器的非循环路径上的一个或多个通信链路的利用的一个或多个利用率值。 然后，该逻辑基于所检索的属性值选择一个内容服务器，并且将该内容的请求发送到所选择的内容服务器。
-
-
-
-
-
-
-
-
-
搜索结果
275 条记录 (耗时 0.037 秒)
