Cisco Technology, Inc.

Chiajen Tsai

Yibin Yang

Liqin Dong

Shyam N Kapadia

Suran Saminda De Silva

Patnala Debashis Rao

Debashis Patnala Rao

Norman William Finn

Ganesh Sundaram

Rick G Chang

Muthumayan Madhayyan

Manish Chandra Agrawal

Larry Tzuchu Chang

Nagabhushan K Channabasappa

Yuchen Zhou

Rajagopalan Janakiraman

Vipin Jain

Palathingal Frank

Chunhui Wong

Vijay Gopal Krishnan

In one embodiment, a network functions virtualization infrastructure can be managed in a decentralized fashion. A front end can receive a request to provision a virtualized network function. The front end can create service descriptors for the request according to the virtualized network function, the service descriptors comprising a hierarchy of information elements organized based on distributed back-end agents operable to provision and manage the virtualized network function. The front end can store the service descriptors in a distributed data store.

System and method of lightweight decentralized NFV orchestration

Systems and methods for triggering service activation include starting a vCPE instance in response to a request for a service, instantiating a service container for the requested service and starting the service in the service container, installing a fast path entry for the service container in a local bridge table, detecting an idle timeout of the service and labeling the local bridge table entry for the corresponding service container as inactive, notifying a cloud services manager that the service container is inactive, and removing the service container.

Datapath triggered on-demand NFV service activation

An example method for facilitating multiple mobility domains with VLAN translation in a multi-tenant network environment is provided and includes detecting attachment of a first virtual machine on a first port and a second virtual machine on a second port of a network element, the first port and the second port being configured with a first mobility domain and a second mobility domain, respectively, and the first and second virtual machines being configured on a same original VLAN, determining whether the original VLAN falls within a pre-configured VLAN range, translating the original VLAN to a first VLAN on the first port corresponding to the first mobility domain and to a second VLAN on the second port corresponding to the second mobility domain, and segregating traffic on the original VLAN into the first VLAN and the second VLAN according to the respective mobility domains for per-port VLAN significance.

Multiple mobility domains with VLAN translation in a multi-tenant network environment

In one embodiment, a method includes detecting a change in network topology and broadcasting a transient unconditional unpruning message to multiple nodes in the network. The message is configured to instruct each of the nodes receiving the message to start a phase timer in response to the broadcast message; unprune its operational ports; and, upon expiration of the phase timer, prune its ports in accordance with the results of a pruning protocol.

Transient unpruning for faster layer-two convergence

Packet transmission techniques are disclosed herein. An exemplary method includes receiving a packet that identifies an internet protocol (IP) address assigned to more than one destination node; selecting a virtual routing and forwarding table based, at least in part, on a segmentation identification in the packet; identifying a designated destination node in the packet based, at least in part, on the selected virtual routing and forwarding table; and transmitting the packet to the designated destination node.

Using segmentation identification to identify destination node within network environment

A leaf switch of a switch fabric includes multiple ports to connect with respective ones of multiple servers. Virtual local area networks (VLANs) are configured on the leaf switch. Dynamic creation of virtual ports is enabled on the leaf switch for at least one of the VLANs on an as needed basis. The leaf switch receives from a particular server connected to a corresponding one of the ports a notification message that a virtual machine is hosted on the particular server. Responsive to the notification message, the leaf switch dynamically creates a virtual port that associates the corresponding one of the ports with the at least one of the VLANs.

Dynamic virtual port instantiation for scalable multitenant network

Some implementations provide a method that includes: (i) receiving a list of logic link aggregations (LAGs) within a computer network, the list identifying a single physical egress port associated with each LAG; (ii) receiving a data unit; (iii) identifying that the data unit is addressed to a remote LAG included in the list of logic link aggregations; (iv) establishing a connection with the remote LAG; (v) downloading a detailed data describing the remote LAG from a control plane, the detailed data including a list of multiple available physical egress ports associated with the remote LAG, and; (vi) upon downloading the detailed data, incorporating the detailed data into the list of LAGs in association with an entry identifying the remote LAG.

System for conversational link aggregation resolution in a network switch

A method is provided in one example and includes receiving, at a receiving node, a packet that comprises information indicative of an internet protocol address and a segmentation identification, selecting a virtual routing and forwarding table corresponding with the segmentation identification, identifying a destination node based, at least in part, on the internet protocol address and the virtual routing and forwarding table, and transmitting the packet to the destination node.

System and method for utilization of a segmentation identification to support transmission of data to a destination node

Methods and apparatuses for rapid TRILL convergence are disclosed herein. The methods can be implemented in a network including a plurality of RBridges or in a cloud network environment including a plurality of cloud switch domains. An example method for rapid TRILL convergence can include: Executing a spanning tree protocol (STP) for network topology in a network; and executing a Hello protocol for control and forwarding at the RBridge. The Hello protocol can be configured to elect a designated RBridge and assign an appointed forwarder. The method can also include assigning a transient appointed forwarder during a period of time between convergence of the STP and convergence of the Hello protocol. The transient appointed forwarder can be configured to forward frames in the network during the period of time between convergence of the STP and convergence of the Hello protocol.

Methods and apparatuses for rapid trill convergence through integration with layer two gateway port

An example method for determining an optimal forwarding path across a network having VxLAN gateways configured to implement both FGL networking and VxLAN capabilities can include learning RBridge nicknames associated with the VxLAN gateways in the network. Additionally, the method can include determining a path cost over the FGL network between each of the VxLAN gateways and a source node and a path cost over the VxLAN between each of the VxLAN gateways and a destination node. Further, the method can include determining an encapsulation overhead metric associated with the VxLAN and selecting one of the VxLAN gateways as an optimal VxLAN gateway. The selection can be based on the computed path costs over the FGL network and the VxLAN and the encapsulation overhead metric.

Optimal forwarding for trill fine-grained labeling and VXLAN interworking

An example method for calculating a constrained distribution tree in a TRILL network including a plurality of VL and FGL RBridges can include learning an FGL multi-destination frame filtering capability of at least one of the FGL RBridges in the TRILL network, constructing a sub-graph including the FGL RBridges and associated links and calculating at least one sub-tree based on the sub-graph. The method can also include constructing a graph including VL RBridges, the FGL RBridges and associated links by adding links between the VL RBridges and the FGL RBridges. The FGL RBridge to which the VL RBridge is linked can have sufficient FGL multi-destination frame filtering capability. Further, the method can include calculating a constrained distribution tree based on the graph by treating the sub-tree as a logical node.

System, devices and methods for facilitating coexistence of VLAN labeling and fine-grained labeling RBridges

A method is provided in one example embodiment and includes establishing at least one fixed topology distribution tree in a network, where the fixed topology distribution tree comprises one root node and a plurality of leaf nodes connected to the root node; maintaining at the root node an indication of multicast group interests advertised by the leaf nodes; and pruning traffic at the root node based on the advertised multicast group interests of the leaf nodes. In one embodiment, the root node is a spine switch and each of the leaf nodes is a leaf switch and each of the leaf nodes is connected to the root node by a single hop.

Efficient handling of multi-destination traffic in an internet protocol fabric data center

A method is provided in one example embodiment and includes determining a route target ('RT') membership for a network element; determining at least one attribute for the RT membership; and advertising the RT membership with the at least one attribute to other network elements. The at least one attribute may include an RT membership type attribute for indicating whether the RT membership is due to a local virtual network connection, transit support, or both. Additionally or alternatively, the at least one attribute may include a distribution tree binding attribute for indicating a distribution tree for the RT membership.

Scalable multicast route distribution in a multitenant data center fabric in a network environment

A method is provided in one example embodiment and includes determining whether a first network element with which a second network element is attempting to establish an adjacency is a client type element. If the first network element is determined to be a client type element, the method further includes determining whether the first and second network elements are in the same network area. If the first network element is a client type element and the first and second network elements are determined to be in the same network area, the adjacency is established. Subsequent to the establishing, a determination is made whether the first network element includes an inter-area forwarder (IAF).

Growing community of inventors

Cupertino, CA, United States of America

Chiajen Tsai