Cisco Technology, Inc.

Manish Bhardwaj

David Delano Ward

Keyur Patel

Steven Vincent Luong

Burjiz F Pithawala

Serpil Bayraktar

Stefano Benedetto Previdi

Jiang Zhu

Huida Dai

Jining Tian

Arjun Sreekantiah

Zhunian Zhang

Christopher Losack

Burjiz Pithawala

Steven V Luong

Embodiments are provided for providing optimal route reflector (ORR) root address assignment to route reflector clients and fast failover capabilities in an autonomous system, including identifying a first node in an autonomous system as a candidate root node of a first routing group, identifying a client node based on a neighbor address used in a first routing protocol, mapping the neighbor address to routing information received from the client node via a second routing protocol, and associating the neighbor address with the first routing group if the routing information includes an identifier of the first routing group. In more specific embodiments, identifying the first node as a candidate root node includes determining the first node and the first routing group are advertised in a first protocol packet, and determining the first node and the second routing group are advertised in a second protocol packet.

Automatic optimal route reflector root address assignment to route reflector clients and fast failover in a network environment

Embodiments are provided for optimized best path selection for optimal route reflection and include configuring, by a cloud-based node, a first cluster of nodes in an autonomous system, and determining whether any paths for a network address prefix are available in the first cluster of nodes. Embodiments also include selecting a best path from one or more paths if the one or more paths are determined to be available in the first cluster for the network address prefix. Embodiments further include advertising the best path to one or more nodes in the first cluster. More specific embodiments include determining, if no paths for the network address prefix are available in the first cluster, another path for the network address prefix is available in a second cluster of nodes of the autonomous system, and selecting the other path as the best path.

Optimized border gateway protocol best path selection for optimal route reflection

Automatic  optimal route reflector root address assignment to route reflector clients and fast failover in a network environment

A network includes a route reflector peered with client routers. From a perspective of the route reflector, a best path to the destination address is selected by applying to candidate paths ordered comparison tests that progress from policy tests through one or more additional tests until the best path is selected. A determination is made as to whether the best path was selected based on the policy tests exclusively. If the best path was selected based on the policy tests exclusively, the best path is assigned to each of the client routers. If the best path was not selected based on the policy tests exclusively, from a perspective of each client router, a respective best path is selected by applying to the candidate paths the one or more additional tests, and the respective best paths are assigned to the respective client routers.

Optimal route reflection using efficient border gate protocol best path selection

In one embodiment, a first network device may receive a request for an identifier of at least one target to service a client. The first network device may obtain an identifier of each of two or more targets. The first network device may then determine whether to redirect the request. The first network device may redirect the request to a second network device according to a result of the determining step, where the first network device is in a first autonomous system and the second network device is in a second autonomous system.

Redirection of requests for target addresses

In one embodiment, a node in a computer network joins a global ring associated with a distributed hash table (DHT), and maintains a DHT routing table and DHT database for the global ring. In addition, the node may determine a particular service class for which the node is configured, and may join a particular service-based sub-ring according to the particular service class, where all nodes of the particular service-based sub-ring are within the global ring. As such, a service-based DHT routing table and service-based DHT database may be maintained for the particular service-based sub-ring, such that DHT operations identified by the particular service class are routed to the particular service-based sub-ring (e.g., by a portal node).

Service-aware distributed hash table routing

In one embodiment, a method comprises identifying prefix groups for searchable character symbols, each prefix group having a corresponding searchable character symbol comprising at least one searchable character; assigning at least one prefix group to each of a plurality of distributed hash table nodes in a network, each distributed hash table node containing at least one of the prefix groups, each distributed hash table node assigned a corresponding prescribed keyspace range of a prescribed keyspace, each distributed hash table node configured for storing data records having respective primary data record keys within the corresponding prescribed keyspace range; and assigning secondary indexes that start with one of the searchable character symbols to the corresponding prefix group in the associated distributed hash table node, enabling any prefix search starting with the one searchable character symbol to be directed to the corresponding prefix group in the associated distributed hash table node.

Prefix and predictive search in a distributed hash table

According to one embodiment, an apparatus that makes improved routing decisions is provided that includes a receiver, a retriever, a proximity engine, and a transmitter. The receiver may be configured to receive a request from a source. The retriever may be configured to retrieve a plurality of providers capable of servicing the request. The proximity engine may be configured to rank the plurality of providers based on weights indicative of a network distance. The weights may correspond to a first Border Gateway Protocol (BGP) community attribute associated with the source and at least a second BGP community attribute associated with at least one of the providers in the plurality of providers. The transmitter may be configured to transmit the request to the provider in the plurality of providers with the highest ranking.

Growing community of inventors

San Francisco, CA, United States of America

Manish Bhardwaj