Abstract: Techniques are provided for optimizing multicast routing in a network. At a router device, a message is sent to one or more physical devices. The message is configured to solicit a response indicating a network assignment for each of the physical devices. A response message is received from each of the physical devices. The response message comprises network assignment information for each of the physical devices. For each of the physical devices, the network assignment information is translated into a segment identifier.

Abstract: Presented herein are techniques to handle data packets received at a top-of-rack (ToR) switch in an underlay network hosting one or more tenant networks. The underlay network may comprise a plurality of ToR switches each connected to each of a plurality of spine switches. The data packet may be received from a virtual machine in a tenant network, and have a header with a data packet identifier. A mobility domain identifier may be determined that corresponds to the network portion within which the virtual machine can be migrated. The mobility domain may be configured on the ToR switch on a per-port basis based on the virtual machine connected to the ToR switch port. A unique identifier may be formed based on the data packet identifier and mobility domain identifier. Using this unique identifier, provisioning information may be obtained for the tenant network on the ToR switch.

Abstract: Techniques are provided for designating, in an overlay transport virtualization (OTV) network connected to a data center, an edge device to act as a backup authoritative edge device (BAED) for an authoritative edge device (AED) for multicast packet encapsulation and forwarding. Data traffic associated with a given virtual local area network (VLAN) may be detected from a multicast source in the data center addressed to recipients in a site group. A mapping may be generated between the site group and a core data group in the OTV network for traffic from the multicast source. Advertisements may be sent of the mapping to edge devices in another data center across the OTV network. A similar configuration is presented for a BAED for inbound multicast traffic to a data center.

Abstract: In one embodiment, an authoritative edge device (AED)-server in a computer network maintains assignment of an active AED for a particular virtual local area network (VLAN), and in response to a triggered re-assignment, sends an AED change request identifying an old active AED for the particular VLAN and a new active AED for the particular VLAN (e.g., and/or corresponding backups). In response to receiving the change request, the old active AED ceases forwarding of traffic for the particular VLAN and transmits a relinquishment confirmation into the network. Also, in response to receiving the change request and the relinquishment confirmation from the old active AED, the new active AED assumes responsibility for traffic forwarding for the particular VLAN and transmits an activation confirmation into the network. The change request is then deemed completed by the AED-sever upon receipt of both the relinquishment confirmation and the activation confirmation.

Abstract: In a mesh-based connected data center network architecture, a mechanism is provided to allow efficient delivery of IP multicast frames within the network. Described approaches avoid replication into VLANs (or SVIs) across the fabric by using the outer encapsulated tree to identify trees on which to replicate the traffic. Replication may be performed at the furthest point from the source (via routing or bridging). Also, multicast traffic may be distributed to dually connected (vPC) hosts on links from various network devices.

Abstract: In one embodiment, a method includes storing a service topology route at a network device interconnecting at least two zones comprising a plurality of hosts, and propagating the service topology route to create a service chain comprising a service node in communication with the network device. The service topology route creates a forwarding state at network devices in the service chain for use in inter-zone routing in a virtual private network. An apparatus and logic are also disclosed herein.

Abstract: Techniques are presented herein for optimizing traffic routing in overlay networks. At a first edge device located at a first site in a network, a message is received that indicates address information of a network device. The address information of the network device is stored in an address table. The address information is associated with a site identifier that identifies a second site at which the network device is located. The site identifier is mapped to an identifier associated with a second edge device that is responsible for routing traffic to network devices at the second site.

Abstract: A method and apparatus to provide network-wide enhanced load balancing. In one embodiment a first message comprising a first value and an address is generated. The first message is transmitted to a first node via a first communication link. A second message comprising a second value and the address is generated. The first and second values are unequal. The second message is transmitted to the first node via a second communication link. Packets are received, wherein each of the packets comprises the address. A first percentage of the packets are forwarded to a first device via the first communication link, wherein the first percentage is proportional to the first value. A second percentage of the packets are forwarded to a second device via the second communication link, wherein the second percentage is proportional to the second value.

Abstract: Techniques are provided for generating and updating flooding tree paths in a network. At a particular node device in a network, a first flooding tree is generated by performing a first shortest path first (SPF) operation from a first selected node device in the network to a plurality of other node devices in the network. A second flooding tree is generated by performing a second SPF operation from a second selected node device in the network to the plurality of other node devices in the network. A network topology change event is detected in either the first or second flooding tree, and a packet sequence exchange is initiated between the particular node device and another node device in the network in response to the detected network topology change. The first and second flooding trees are then updated based on information obtained during the packet sequence exchange.

Abstract: According to one embodiment, a method includes receiving, by a first edge device at a first site, a first site overlay control plane message including control plane information. The first edge device translates the first site overlay control plane message into a core overlay control plane message. The first edge device sends the core overlay control plane message over a core network to a second edge device at a second site.

Abstract: In one embodiment, a method includes receiving a packet at an edge device in a first network site in communication with a second network site through a transport network, the packet comprising a destination address for a host at the second network site, verifying at the edge device a connection with the host, and inserting the destination address in a forwarding information base at the edge device upon verifying the connection with the host. An apparatus and logic are also disclosed herein.

Abstract: Methods and systems may be provided for detecting the moves of a multicast source. Sites that were previously designated as an active source may be immediately expired instead of waiting for route expiry. All multicast receiver sites may deterministically learn the new multicast source without additional LSP churn in ISIS for resolving the multicast source move conflict between the old and new source sites.

Abstract: In some embodiments, edge devices associated with a network segment are identified. One of the devices is elected as an authoritative device and any previous authoritative devices are instructed to halt forwarding network traffic to an overlay network.

Abstract: In one embodiment, a method at a network device includes receiving a link layer advertisement, comparing information in the link layer advertisement with connectivity information stored at the network device, and based on the comparison, determining if there is a cabling error between the network device and a link peer transmitting the link layer advertisement. An apparatus and logic are also disclosed herein.

Abstract: Techniques are provided for two peer edge switches in an edge switch cluster of a first data center site to actively provide traffic flow redundancy in an active-active configuration and provide multi-homing support over an overlay transport virtualization (OTV) protocol. Information is stored indicating a media access control (MAC) address of at least one endpoint device at the first site. An edge switch in the edge switch cluster at the first site sends via an OTV protocol a Layer-3 message that is configured to advertise the MAC address of the at least one endpoint at the first site to enable at least one edge switch at a second site to perform multipath routing to the endpoint device at the first site based on each of the edge switches in the edge switch cluster at the first site.

Abstract: A first addressing message is received at a first switch in a network fabric indicating that a first virtual machine has undergone migration from connection to a first virtual switch at a first server to connection to a second virtual switch at a second server. A route advertisement message is then transmitted from the first switch to at least a second switch in the network fabric. This route advertisement is configured to cause the second switch to transmit a second addressing message to a second virtual machine connected to the first virtual switch. The second addressing message provides the second virtual machine with updated addressing information for the first virtual machine. A third addressing message is also transmitted from the first switch to the first virtual machine to provide the first virtual machine with updated addressing information for the second virtual machine.

Abstract: In one embodiment, an apparatus includes one or more internal interfaces in communication with one or more network devices in a first network site through a Layer 2 link, an overlay interface in communication through a Layer 3 link with a core network connected to one or more other network sites, and a table mapping addresses for network devices in the other network sites to addresses of edge devices in the same network site as the network device. The apparatus further includes a processor operable to encapsulate a packet received at one of the internal interfaces and destined for one of the network devices in the other network sites, with an IP header including a destination address of the edge device mapped to the destination network device, and forward the encapsulated packet to the core network.

Abstract: Devices, methods and instructions encoded on computer readable medium are provided herein for creation of an overlay network on a non-multicast or source specific multicast (SSM) core. In one example, virtual private network (VPN) adjacencies are established between an adjacency server and one or more edge devices each located at different network sites. A unicast replication list is then generated at the adjacency server. The unicast replication list includes the Internet Protocol addresses for each of the edge devices having VPN adjacencies with the adjacency server. The unicast replication list is then advertised to each of the edge devices for use in establishing VPN adjacencies with one another.

Abstract: Devices, methods and instructions encoded on computer readable medium for implementation of a dual-adjacency between edge devices of a network site. A first edge device comprises one or more local interfaces configured for communication, via a local network, with one or more network devices co-located in a first network site. The first edge device also comprises one or more overlay interfaces configured for communication, via a core network, with one or more network devices located in one or more other network sites connected to the core network. The first edge device comprises a processor configured to establish, via at least one of the local interfaces, a site communication channel with a second edge device co-located in the first network site. The processor is further configured to establish an overlay communication channel, via at least one of the overlay interfaces, with the second edge device.

Abstract: In one embodiment, a method includes building an address resolution cache for a layer-3 router in a first layer-2 datacenter, where the address resolution cache includes a plurality of entries, each of the entries containing a host network address, a host hardware address, and a switch identifier for a switch serving a host, intercepting an address resolution flood within the first layer-2 datacenter that seeks address resolution for a host in a second layer-2 datacenter, and generating a response to the address resolution flood that indicates a source in the second layer-2 datacenter, where data indicating the source in the second layer-2 datacenter is accessed from the address resolution cache.