Cisco Technology, Inc.

Future Wei Technologies, Inc.

Cisco Systems Inc.

Huawei Technologies Co., Limited

Shujin Zhang

Shuxian Lou

Aravind Sitaraman

Maria Alice Dos Santos

Jie Chu

Jane Jiaying Jin

Xi Xu

Sampath Kumar Sthothra Bhasham

Renwei Li

Lin Han

Katherine Zhao

Dennis James Cox

John A Joyce

Roman Peter Kochan

Xiaoqian Wu

Bernard Roycroft James

Rene T Tio

Peter S Heitman

Tianji Jiang

Aziz Abdul

Jiang Zhu

Jan Medved

Subrata Banerjee

Ming Li

Xiaoyong Yi

Charles Troper Yager

Sukhdev S Kapur

Ashok Ganesan

Leslie Alan Thomas

Purnam Anil Sheth

Huida Dai

Xuesong Dong

Bisong Tao

Hongtao Yin

Danny J Elder

Jayadev Kumarasamy

Joshua Merrill

Houshang Nayeb Hosseini

Pinzhong Liu

Yonghui Wu

Xiao Gong

A network controller may receive a request from an application via an application programming interface (API), wherein the request comprises program codes written in a declarative programming language, and wherein the program codes describe at least some aspects of a virtual network (VN). The network controller may further parse the program codes into internal objects of the network controller, with the internal objects representing the aspects of the VN described by the program codes. The network controller may then manage the VN according to the internal objects translated from the program codes.

Declarative approach to virtual network creation and operation

A method for network control, comprising receiving a request for a network view from an application at a Software Defined Network (SDN) controller, creating a network view from a network map, wherein the network map comprises a representation of a plurality of network devices and network paths in a SDN-based multiple layer network, and wherein the network view comprises at least a portion of the devices or paths in the network map, and sharing the network view with the application.

Methods of representing software defined networking-based multiple layer network topology views

A method for internet traffic management, comprising receiving a request for a path set from an application at a network traffic controller, wherein the request contains an intended traffic destination endpoint, evaluating a plurality of network devices in a network, identifying a plurality of paths usable by the application to transmit traffic from the application to the intended traffic destination endpoint, including the plurality of paths in the path set, and sharing the path set with the application.

Method for internet traffic management using a central traffic controller

A network component for supporting packet forwarding in a United Router Farm (URF), the network component comprising a processor configured to receive a packet, encapsulate the packet using a URF header comprising a URF Layer Two (L2) header that indicates Media Access Control (MAC) addresses of current and next hops, an outer label that indicates a tunnel to a destination node in the URF, and an inner label that indicates an egress port on the destination node, and send the packet to a next hop in the URF after encapsulating the packet.

Method of multiprotocol label switching encapsulation for united router farm forwarding

One embodiment of the present invention provides a computing system. The computing system includes a processor, a memory, a logical switch management mechanism, and a layer-2 path management mechanism. The logical switch management mechanism operates the computing system in conjunction with a plurality of remote switches as a single logical switch. The layer-2 path management mechanism includes a path calculation mechanism and a layer-2 forwarding table. The path calculation mechanism calculates layer-2 shortest paths among the computing system and the remote switches. The layer-2 forwarding table is for a first switch in the plurality of remote switches and created based on one or more of the shortest paths, wherein a respective entry in the forwarding table corresponds to a layer-2 network address. The layer-2 path management mechanism suppresses advertisement of the shortest paths outside of the logical switch, thereby hiding internal paths of the logical switch.

Layer-3 services for united router farm

In one embodiment, a method comprises receiving a request for a distributed service, the distributed service offered by a service provider via a data communications network having service delivery locations reachable via a prescribed physical topology; identifying the service delivery locations within a prescribed logical topology overlying the prescribed physical topology, the prescribed logical topology segregating the distributed service from other network traffic on the prescribed physical topology; and identifying one or more of the service delivery locations optimized for providing the distributed service to at least one service consumption location in the prescribed logical topology according to a prescribed service level agreement with the service provider.

Placement of service delivery locations of a distributed computing service based on logical topology

One embodiment of the present invention provides a computing system. The computing system includes a processor, a memory, a discovery mechanism, a switch management mechanism, and a configuration management mechanism. The discovery mechanism discovers a remote switch. The switch management mechanism registers the remote switch and transmits a switch image to the remote switch, thereby allowing the remote switch to install the image. The configuration management mechanism configures the remote switch, thereby allowing the remote switch to be controlled by the computing system.

United router farm setup

A system for identifying a subscriber includes an access server coupled to a number of subscribers using a first communication network and further coupled to a second communication network, a memory coupled to the access server, and a processor coupled to the memory. The access server receives a communication from a particular subscriber using a particular one of a number of virtual circuits associated with the first communication network. The memory stores path information that identifies a virtual circuit assigned to the particular subscriber. The processor identifies the particular subscriber for connection to the second communication network based upon the path information and the particular virtual circuit used to receive the communication from the particular subscriber.

System and method for identifying a subscriber for connection to a communication network

A network access server (NAS) provides a connection to a user in a data communications network, where the NAS is capable of communicating with a home gateway server (HGS) maintaining a pool of IP addresses for allocation to authorized users associated with the NAS. The NAS includes a first memory for storing an identification of a user, an requester for asking the HGS for an IP address on behalf of the user; and a second memory associated with the first memory for storing the IP address of the user received from the HGS. The NAS may further include a detector for periodically detecting connection of the user to the NAS and a keep-alive sender for periodically informing the HGS that the user is still connected to the NAS, a receiver for receiving periodic queries from the HGS about the status of the user connection to the NAS and a responder responsive to said periodic queries for informing the HOS that the use is still connected to the NAS, and/or a receiver for receiving periodic signals from the user and a forwarder responsive to said receiver for forwarding information to the HGS that the user is still connected to the NAS. A home gateway server (HOS) provides mechanisms to assign an IP address to a user via a NAS, and to monitor the status of the IP address after assignment.

IP address allocation in a network environment

A method for routing packets sent from a user to the internet is provided for systems in which the user is connected to a private network. The method includes: extracting a source network address from the packet; using said source network address to retrieve a user profile for the user; examining said user profile to determine whether to route the packet through the private network or to route the packet directly to the Internet; and routing said packet according to said profile. This allows a user or network provider to choose whether to route packets destined for the Internet directly to the Internet rather than through the private network, thus preventing excessive network traffic on the private network.

Default internet traffic and transparent passthrough

This invention provides a method and apparatus for issuing or renewing a host address. The apparatus has an input device to receive a data packet having a host identifier, a memory to store a list of host identifiers, and a processor to match the host identifier with the list of host identifiers. If a match is found, an output device transmits the data packet to an address allocation device to issue or renew the host address. The method provides for retrieving the host identifier in the header of the data packet, matching the host identifier with a list of host identifiers, and maintaining a state of authentication for the host if a match is found, otherwise maintaining a state of unauthentication for the host. The method further provides for inserting a proxy address in a relay agent address field, setting a flag, and transmitting the data packet to an address allocation device to issue or renew the host address. The proxy address is also set in a server identifier address field and the flag is unflaged before any data packets are forwarded to the host.

Proxy for network address allocation

Service requests, which are used to properly process a network access request received from a client, are processed by routing the service requests between at least two service component instances according to a load balancing algorithm. Load balancing includes: calculating a first ticket amount and a second ticket amount; assigning the first ticket amount to a first instance and the second ticket amount to a second instance; using a selection scheme to select an instance having a ticket amount greater than a threshold amount to process a service request; decrementing the ticket amount corresponding to the instance selected; and scheduling the instance selected to receive a service request. The present invention may further include distinguishing between operable and inoperable instances, providing ticket amounts that are not based on performance ratings to inoperable instances, and providing ticket amounts that are based on performance ratings to operable instances.

Load balancing between service component instances

A network access server (NAS) provides a connection to a user in a data communications network, where the NAS is capable of communicating with a home gateway server (HGS) maintaining a pool of IP addresses for allocation to authorized users associated with the NAS. The NAS includes a first memory for storing an identification of a user, a requester for asking the HGS for an IP address on behalf of the user; and a second memory associated with the first memory for storing the IP address of the user received from the HGS. The NAS may further include a detector for periodically detecting connection of the user to the NAS and a keep-alive sender for periodically informing the HGS that the user is still connected to the NAS, a receiver for receiving periodic queries from the HGS about the status of the user connection to the NAS and a responder responsive to the periodic queries for informing the HGS that the user is still connected to the NAS, and/or a receiver for receiving periodic signals from the user and a forwarder responsive to the receiver for forwarding information to the HGS that the user is still connected to the NAS. A home gateway server (HGS) provides mechanisms to assign an IP address to a user via a NAS, and to monitor the status of the IP address after assignment.

A gateway routes a packet from a user to a connected network utilizing a per-user routing table. A source address is extracted from the packet; a per-user routing table corresponding to the source address is found, the per-user routing table contains entries corresponding to one or more currently accessible networks for the user and the range of network addresses corresponding to the currently accessible networks; a destination address is extracted from the packet; an entry in the matching per-user routing table with a range of network addresses containing the destination address is sought; the packet is routed to a matching network if the destination address is contained within one of the ranges of network addresses for the currently accessible networks ('ranges'); and the packet is routed to a default network if the destination address is not contained within one of the ranges. Different users may access a different set of networks and select a desired network for access.

Per user and network routing tables

Multiple simultaneous network connections from a single PPP connection may be accomplished by utilizing a gateway in the following manner. A first network connection is established between the gateway and a first network. A first real network address for the user is then received, the first real network address assigned by the first network. Then, the gateway may establish a network session between the gateway and a second network and receive a second real network address for the user, the second real network address assigned by the second network. A virtual network address may be assigned to the user for network address translation purposes. Additional network connections may be added in a similar manner. Network address translation is then performed on packets traveling between the user and any of the network sessions. This allows each of the simultaneous network connections to gain the benefits of network address translation.

Growing community of inventors

San Carlos, CA, United States of America

Shujin Zhang