Juniper Networks, Inc.

Pedro R Marques

Harshad Bhaskar Nakil

Ankur Singla

Ashish Ranjan

Ina Minei

Rajashekar Reddy

Hampapur Nagaraj Ajay

Der-Hwa Gan

Steven Lin

Yakov Rekhter

Nischal Sheth

Tirthankar Ghose

Nd Ramesh

In general, techniques are described for configuring and managing virtual networks. For example, a distributed virtual network controller is described that configures and manages an overlay network within a physical network formed by plurality of switches. A plurality of servers are interconnected by the switch fabric, each of the servers comprising an operating environment executing one or more virtual machines in communication via the overlay networks. The servers comprises a set of virtual switches that extends the overlay network as a virtual network to the operating environment of the virtual machines. The controller may instruct the servers and the virtual switches to perform various operations, such as determining a physical network path taken by packets of a network packet flow, determining latency through the network, re-routing traffic in the virtual network due to network events, replicating traffic for multicasting, providing multi-tenant services to support multiple virtual networks, monitoring and logging traffic characteristics within the virtual networks and other operations.

Distributed virtual network controller

In general, techniques are described for automated traffic mapping for multi-protocol label switching (MPLS) networks. A network device comprising a processor and an interface card may perform the techniques. The processor may generate an advertisement that conforms to a routing protocol. The advertisement may advertise a mapping between a network flow and a label switched path (LSP) tag. The processor may also generate a communication associating the label switched path tag with an LSP. The interface card may transmit the advertisement to a head-end label edge router that admits traffic into the LSP identified by the LSP tag. The interface card may also transmit the communication to the label edge router such that the label edge router is able to process the communication in conjunction with the advertisement to map the network flow to the LSP identified by the LSP tag.

Automatic traffic mapping for multi-protocol label switching networks

In general, techniques are described in which a plurality of network switches automatically configure themselves to operate as a single virtual network switch. A virtual switch is a collection of individual switch devices that operate like as single network switch. As described herein, network switches in a network that are capable of participating in a virtual switch may automatically discover one another. The participating network switches may then elect one of the participating switches as a master switch. The master switch may generate forwarding information and store the forwarding information in the participating switches, including the master switch. The forwarding information causes the participating switches to act like a single network switch.

Automatic configuration of virtual network switches

Techniques are described to provide multicast service within a virtual network using a virtual network controller and endpoint replication without requiring multicast support in the underlying network. The virtual network controller is configured to create a multicast tree for endpoint devices of a multicast group in the virtual network at a centralized location instead of in a distributed fashion. The virtual network controller communicates the multicast tree to one or more of the endpoint devices of the multicast group to instruct the endpoint devices to replicate and forward multicast packets to other endpoint devices according to the multicast tree. The replication and forwarding of multicast packets is performed by virtual switches executed on the endpoint devices in the virtual network. No replication is performed within the underlying network. The techniques enable multicast service within a virtual network without requiring multicast support in the underlying network.

Multicast service in virtual networks

In general, techniques are described for facilitating multi-tenancy of a server accessed by virtual networks of a data center. A device included within a data center comprising one or more processors may perform the techniques. The processors may be configured to execute a virtual switch that supports a number of virtual networks executing within the data center. The virtual switch may be configured to receive a request regarding data associated with an identifier that is unique within one of the virtual networks that originated the request. The virtual switch may then translate the identifier included within the request to generate a globally unique identifier that is unique within the plurality of virtual networks, update the request to replace the identifier included within the request with the globally unique identifier, and transmit the updated request to a server of the data center.

Multitenant server for virtual networks within datacenter

In one example, a network device includes a virtual network agent, and a network interface to send network packets to the virtual network controller using a default route for a physical network prior to establishing a communication session between a virtual network controller and the virtual network agent, wherein, after establishing the communication session between the virtual network controller device and the virtual network agent, the virtual network agent receives from the virtual network controller a command to install a new route at the network device, wherein the new route specifies encapsulation information to use for encapsulating network packets for sending the network packets to the virtual network controller over an overlay network, and wherein, responsive to detecting a failed link in the physical network, the virtual network agent sends packets to the virtual network controller on an alternate route in the overlay network.

Re-routing network traffic after link failure

Constraint information associated with peering links is taken into account when establishing label switched paths (LSPs) to exit points of a network. Devices within the network, such as routers, designate interfaces associated with peering links as 'passive interfaces' to indicate that the interfaces should be included for bandwidth accounting purposes and internal path computation. Other devices within the network utilize the constraint information, e.g., bandwidth availability, when computing and establishing LSPs to the exit points of the network to avoid congested peering links.

RSVP-passive interfaces for traffic engineering peering links in MPLS networks

Label distribution protocol (LDP) signaled label-switched paths (LSPs) are supported without requiring information about remote autonomous systems (ASs) to be injected into the local interior gateway protocol (IGP). This may be done by (i) decoupling a forwarding equivalency class (FEC) element from the routing information, and (ii) specifying a next hop on which the FEC relies. An LDP messaging structure (e.g., an LDP type-length-value (TLV)) that includes a label, FEC information (e.g., a host address or prefix of an egress LSR of the LSP) and a next hop (e.g., a host address or prefix of a border node, such as an AS border router (ASBR)) may be provided. This messaging structure may be included in one or more of (a) label mapping messages, (b) label withdraw messages, and (c) label release messages. If an LDP message including the expanded LDP messaging structure is received at a node, the node may determine whether or not to propagate the LSP using the next hop information, rather than the FEC information. If, on the other hand, the LDP message includes a normal LDP messaging structure, the node may determine whether or not to propagate the LSP as usual.

Controlling the signaling of label-switched paths using a label distribution protocol employing messages which facilitate the use of external prefixes

A system distributes extended traffic accounting information of bandwidth availability on links throughout a network. For example, routers within the network utilize an extended reservation protocol to calculate bandwidth availability information for links. In calculating the bandwidth availability information, the extended reservation protocol accounts for not only the amount of bandwidth reserved on each of links via the resource reservation protocol itself, but also for the bandwidth usage by other traffic on the links, such as Label Distribution Protocol (LDP) traffic or Internet Protocol (IP) traffic. The routers exchange bandwidth availability information using a routing protocol to gain network-wide knowledge of bandwidth availability.

Traffic engineering using extended bandwidth accounting information

A routing protocol, such as the Border Gateway Protocol (BGP), is extended in a manner that allows the protocol to opaquely carry routing attributes associated with an origin of a routing advertisement, e.g., a customer network of associated with a virtual private network (VPN). These attributes are carried within routing communications using a separate attribute set, and are automatically utilized when delivering the routing advertisement to other customer networks associated with the VPN. As a result, the customer networks are isolated from the routing attributes used within an intermediate network coupling the customer networks.

Providing transparent virtual private network connectivity across intermediate networks

A method for enabling autonegotiation over an interface for which no autonegotiation standard exists comprises establishing network communication between a first network device and a second network device over a communication link. The first network device includes a first media access controller (MAC) associated with a communication port coupled to the communication link and a second MAC positioned between the first MAC and the communication port, and the second MAC operates as a proxy MAC for the first MAC. The first MAC outputs an outbound data communication to the communication port at a first communication rate. The proxy MAC intercepts the outbound data communication. The proxy MAC then outputs the outbound data communication to the communication port at a second communication rate different from the first communication rate.

Autonegotiation over an interface for which no autonegotiation standard exists

A device includes a primary control unit and a standby control unit. The standby control unit records routing communications exchanged between the primary control unit and an external routing device in accordance with a routing protocol. A standby routing process executing on the standby control unit processes the recorded routing communications when the primary control unit fails. The standby routing process generates state information for executing the routing protocol on the standby control unit without requiring that routing sessions be reestablished with the external routing device.

Growing community of inventors

Sunnyvale, CA, United States of America

Pedro R Marques