公开(公告)号：US09369408B1

公开(公告)日：2016-06-14

申请号：US14176625

申请日：2014-02-10

Applicant: Google Inc.

Inventor： Barath Raghavan ,  Subhasree Mandal ,  Mohammad Alfares ,  John Mccullough ,  Fei Ye ,  Min Zhu ,  Aravind Ravisankar

IPC: G01R31/08 ,  H04L12/939 ,  H04L12/26

CPC classification number: H04L49/557 ,  H04L43/08 ,  H04L43/0888

Abstract: Aspects and implementations of the present disclosure generally relate to use of a multi-chassis link aggregation for high performance and resilience in wide-area networking. In one aspect, the disclosure relates to a system that includes a switch fabric. The fabric includes at least a plurality of edge network devices, a set of internal switch devices, and a plurality of internal network links coupling each edge network device to at least a subset of the set of internal switch devices. The system includes a network controller coupled to the switch fabric, configured to maintain at least one link aggregation comprising a logical grouping of externally facing network interfaces of at least two of the plurality of edge devices. The network controller is configured to monitor internal link performance characteristics and determine throughput characteristics for each link aggregation over time based at least in part on current internal link performance characteristics.

Abstract translation: 本公开的方面和实施方式一般涉及在多区域网络中使用多机箱链路聚合以实现高性能和弹性。 一方面，本发明涉及一种包括交换结构的系统。 该结构包括至少多个边缘网络设备，一组内部交换设备和将每个边缘网络设备耦合到该组内部交换机设备的至少一个子集的多个内部网络链路。 该系统包括耦合到交换结构的网络控制器，被配置为维持至少一个链路聚合，其包括多个边缘设备中的至少两个的外部面向的网络接口的逻辑分组。 网络控制器被配置为至少部分地基于当前的内部链路性能特征来监视内部链路性能特征并且确定每个链路聚合随时间的吞吐量特性。

公开(公告)号：US20140355415A1

公开(公告)日：2014-12-04

申请号：US14459670

申请日：2014-08-14

Applicant: Google Inc.

Inventor： Subhasree Mandal ,  Subbaiah Venkata ,  Leon Poutievski ,  Amit Gupta ,  Min Zhu ,  Rajiv Ramanathan ,  James M. Wanderer ,  Joon Ong

IPC: H04L12/24 ,  H04L12/703

CPC classification number: H04L41/0668 ,  H04L41/12 ,  H04L45/28 ,  H04L45/38 ,  H04L45/42 ,  H04L45/64

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for semi-centralized routing. In one aspect, a computer-implemented method receives a network protocol packet at a router adapted for routing data packets to one or more additional routers. The network protocol packet conforms to a routing protocol that provides distributed routing computation. The method also sends the network protocol packet, through a controller, to a selected one of a plurality of route control servers. The method also processes the network control packet at the selected route control server to generate a routing computation result that conforms to the routing protocol. The method also generates routing information based on the routing computation. The routing information conforms to a control protocol that provides centralized routing computation. The method also sends the routing information to the router for routing of data packets based on the control protocol.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于半集中式路由。 在一个方面，计算机实现的方法在适于将数据分组路由到一个或多个附加路由器的路由器处接收网络协议分组。 网络协议分组符合提供分布式路由计算的路由协议。 该方法还通过控制器将网络协议分组发送到多个路由控制服务器中的所选择的一个。 该方法还处理所选择的路由控制服务器上的网络控制分组，以生成符合路由协议的路由计算结果。 该方法还基于路由计算生成路由信息。 路由信息符合提供集中式路由计算的控制协议。 该方法还根据控制协议将路由信息发送给路由器进行路由数据包路由。

公开(公告)号：US09942156B1

公开(公告)日：2018-04-10

申请号：US15183228

申请日：2016-06-15

Applicant: Google Inc.

Inventor： Junlan Zhou ,  Min Zhu ,  Amin Vahdat

IPC: H04L12/26 ,  H04L12/803 ,  H04L12/721 ,  H04L12/741 ,  H04L12/733

CPC classification number: H04L47/125 ,  H04L45/20 ,  H04L45/38 ,  H04L45/74 ,  H04L47/11

Abstract: Exemplary embodiments allocate network traffic among multiple paths in a network, which may include one or more preferred paths (e.g. shortest paths) and one or more alternative paths (e.g., non-shortest paths). In one embodiment, network traffic in form of flows may be allocated to the preferred paths until the allocation of additional network traffic would exceed a predetermined data rate. Additional flows may then be sent over the alternative paths, which may be longer than the preferred path. The paths to which each flow is assigned may be dynamically updated, and in some embodiments the path assignment for a particular flow may time out after a predetermined time. Accordingly, the flow traffic of each path may be balanced based on real-time traffic information.

公开(公告)号：US09559985B1

公开(公告)日：2017-01-31

申请号：US14216433

申请日：2014-03-17

Applicant: GOOGLE INC.

Inventor： Fei Ye ,  Subhasree Mandal ,  Wei Sun ,  Min Zhu

IPC: H04L12/933 ,  H04L12/54

CPC classification number: H04L49/15 ,  H04L12/56 ,  H04L12/5601 ,  H04L45/12 ,  H04L49/1515 ,  H04L49/1569 ,  H04L49/256

Abstract: A technique includes determining a first set of intra-node port weights for a first switch of a first routing node, determining a set of inter-node port weights including a first inter-node port weight for routing traffic to a second routing node, determining a first inter-node weighted port group for the first switch for traffic directed to the second routing node, the first inter-node weighted port group including a first total port weight based on a first intra-node port weight and the first inter-node port weight and which is applied to a first port of the first switch, and a second total port weight based on a second intra-node port weight and the first inter-node port weight and which is applied to the second port of the first switch, and routing traffic to an output port of the first switch based on the first inter-node weighted port group.

Abstract translation: 一种技术包括确定第一路由节点的第一交换机的第一组节点内端口权重，确定一组节点间端口权重，包括用于将业务路由到第二路由节点的第一节点间端口权重，确定 第一节点间加权端口组，用于针对第二路由节点的流量的第一交换机，所述第一节点间加权端口组包括基于第一节点内端口权重的第一总端口权重和所述第一节点间节点 端口权重，并且被应用于第一交换机的第一端口，以及基于第二节点内端口权重和第一节点间端口权重的第二总端口权重，并且被应用于第一交换机的第二端口 并且基于第一节点间加权端口组将流量路由到第一交换机的输出端口。

公开(公告)号：US09379981B1

公开(公告)日：2016-06-28

申请号：US14039611

申请日：2013-09-27

Applicant: Google Inc.

Inventor： Junlan Zhou ,  Min Zhu ,  Amin Vahdat

IPC: H04L12/26 ,  H04L12/803

CPC classification number: H04L47/125 ,  H04L45/20 ,  H04L45/38 ,  H04L45/74 ,  H04L47/11

Abstract: Exemplary embodiments allocate network traffic among multiple paths in a network, which may include one or more preferred paths (e.g. shortest paths) and one or more alternative paths (e.g., non-shortest paths). In one embodiment, network traffic in form of flows may be allocated to the preferred paths until the allocation of additional network traffic would exceed a predetermined data rate. Additional flows may then be sent over the alternative paths, which may be longer than the preferred path. The paths to which each flow is assigned may be dynamically updated, and in some embodiments the path assignment for a particular flow may time out after a predetermined time. Accordingly, the flow traffic of each path may be balanced based on real-time traffic information.

Abstract translation: 示例性实施例在网络中的多个路径之间分配网络业务，其可以包括一个或多个优选路径（例如，最短路径）和一个或多个备选路径（例如，非最短路径）。 在一个实施例中，可以将流形式的网络流量分配给优选路径，直到附加网络流量的分配将超过预定数据速率。 然后可以通过替代路径发送附加流，其可以比优选路径更长。 分配每个流的路径可以被动态地更新，并且在一些实施例中，特定流的路径分配可以在预定时间之后超时。 因此，可以基于实时交通信息来平衡每个路径的流量。

公开(公告)号：US09491102B1

公开(公告)日：2016-11-08

申请号：US14176518

申请日：2014-02-10

Applicant: Google Inc.

Inventor： Junlan Zhou ,  Min Zhu ,  Amin Vahdat

IPC: H04L12/26 ,  H04L12/803 ,  H04L12/66 ,  H04L12/46 ,  H04L12/715

CPC classification number: H04L47/125 ,  H04L12/4625 ,  H04L12/4633 ,  H04L12/66 ,  H04L43/0882 ,  H04L45/64

Abstract: A technique for load balancing in a multi-topology network selects a network path having a favorable bandwidth*hop count product. Accordingly, shorter paths are prioritized while longer paths are used for traffic load balancing when appropriate. For example, a telecommunications network may employ a Clos-style topology in which hosts are connected to each other through multiple hierarchical levels of forwarding devices. One or more high level switches may be removed, creating isolated blocks of forwarding devices. The blocks may be connected by the remaining original high level Clos-style topology switch(es) and a second type of network topology. In an exemplary embodiment, traffic may be scheduled over routes with the following decreasing priorities: (1) the shortest path, using either or both network topologies; (2) a path using only a single network topology type; (3) non-shortest paths between directly-connected blocks; and (4) non-shortest paths between indirectly-connected blocks.

Abstract translation: 在多拓扑网络中进行负载平衡的技术选择具有有利带宽跳跃计数乘积的网络路径。 因此，在适当的情况下，较长的路径用于流量负载平衡，优先考虑较短的路径。 例如，电信网络可以采用Clos式拓扑，其中主机通过多个层次级的转发设备相互连接。 可以去除一个或多个高级交换机，从而创建隔离的转发设备。 块可以由剩余的原始高级Clos风格的拓扑交换机和第二类型的网络拓扑连接。 在示例性实施例中，可以通过具有以下降低优先级的路由来调度业务：（1）使用网络拓扑中的一个或两个的最短路径; （2）仅使用单个网络拓扑类型的路径; （3）直接连接块之间的非最短路径; 和（4）间接连接的块之间的非最短路径。