Abstract: In one embodiment, a method includes detecting a change in network topology and broadcasting a transient unconditional unpruning message to all nodes in the network. The message is configured to instruct each network element 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.

Abstract: Techniques are presented for distributing host route information of virtual machines to routing bridges (RBridges). A first RBridge receives a routing message that is associated with a virtual machine and is sent by a second RBridge. The routing message comprises of mobility attribute information associated with a mobility characteristic of the virtual machine obtained from an egress RBridge that distributes the routing message. The first RBridge adds a forwarding table attribute to the routing message that indicates whether or not the first RBridge has host route information associated with the virtual machine in a forwarding table of the first RBridge. The first RBridge also distributes the routing message including the mobility attribute information and the forwarding table attribute, to one or more RBridges in the network.

Abstract: A segment within a virtual network is identified as being supported by a segment bundling device. The segment within the virtual network supports a first host connected to a first bridging device and a second host connected to a second bridging device. The segment bundling device is used to receive virtual network address information describing the virtual network segmentation identifier (ID) for the segment used for receiving virtual network traffic for the first and second host. A segment bundling table associating a bundle ID with the virtual network segmentation identifier based on the upper ID and the lower ID of the virtual network ID is generated by the segment bundling device. The segment bundling device is used to distribute the segment bundling table to traffic forwarding devices in the virtual network that interface with the first bridging device and the second bridging device.

Abstract: In one embodiment, a plurality of leaf switches that include host facing ports are configured as a cloud switch. An indication of connectivity between the leaf switches of the cloud switch and routing bridges (RBridges) external to the cloud switch may be added to link state packets (LSPs) sent over the at least one logical shared media link. A lookup table may be generated that specifies next hop leaf switches. The generated lookup table may be used to forward frames to one or more particular nexthop leaf switches. Further, traffic engineering parameters may be collected. Equal cost multipath (ECMP) nexthop leaf switches and distribution trees to reach one or more destinations may be examined. Traffic may be distributed across ones of them based on the traffic engineering parameters.

Abstract: Techniques are provided for managing movements of virtual machines in a network. At a first switch, a virtual machine (VM) is detected. The VM is hosted by a physical server coupled to the first switch. A message is sent to other switches and it indicates that the VM is hosted by the physical server. When the first switch is paired with a second switch as a virtual port channel (vPC) pair, the message includes a switch identifier that identifies the second switch. A receiving switch receives the message from a source switch in the network comprising a route update associated with the VM. A routing table of the receiving switch is evaluated to determine whether the host route is associated with a server facing the physical port. The message is examined to determine it contains the switch identifier.

Abstract: 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).

Abstract: 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.

Abstract: In one embodiment, a first number of multiple spanning tree instances (MSTIs) are defined within a network. A second number of network segments associated with segmentation identifier (IDs) are also configured, where the first number of MSTIs is less than the second number of segmentation IDs. Segmentation ID to MSTI mappings are maintained that map each defined segmentation ID of the second number of network segments to one of the first number of MSTIs. A segmentation mapping digest is computed of the segmentation ID to MSTI mappings. Multiple spanning tree (MST) bridge protocol data units (BPDUs) are broadcast that include the digest of the segmentation ID to MSTI mappings.

Abstract: In one embodiment, a plurality of leaf switches that include host facing ports are configured as a cloud switch. An indication of connectivity between the leaf switches of the cloud switch and routing bridges (RBridges) external to the cloud switch may be added to link state packets (LSPs) sent over the at least one logical shared media link. A lookup table may be generated that specifies next hop leaf switches. The generated lookup table may be used to forward frames to one or more particular nexthop leaf switches. Further, traffic engineering parameters may be collected. Equal cost multipath (ECMP) nexthop leaf switches and distribution trees to reach one or more destinations may be examined. Traffic may be distributed across ones of them based on the traffic engineering parameters.

Abstract: In Service Software Upgrade (ISSU) permits administrators to upgrade the control plane software of a network device without any disruption to the traffic passing through the data plane of the network device. However, because the control plane is unavailable, the network device is unable to transmit periodic messages to re-subscribe to specific VLANs. This may result in a service outage in end devices that rely on the network device to receive data assigned to those VLANs. To prevent the network device from being unsubscribed from the VLANs while the control plane is unavailable, the network device may transmit a control plane message before starting ISSU. Once a neighboring network device receives the message, the neighboring device delays unsubscribing the network device until the control plane is again available. Thus, the network device may perform ISSU without the possibility of data traffic not reaching end devices.

Abstract: Techniques are provided for managing and distributing communications in a network. At a first switch device arranged in a first configuration in a network, a set of one or more network attributes are determined, which are associated with network communications that the first switch device is interested in receiving from other network devices. The first switch device sends to a controller device an attribute interest message that informs the controller device of the set of network attributes. The first switch device receives a mapping of the network attributes in to one or more identifiers. The identifiers are included in a header of subsequent frames sent in the network. An identifier interest message is then sent to a second switch device arranged in a second network configuration in the network to inform the second switch device of identifiers of the network attributes of which the first device has an interest.

Abstract: An example method includes storing a portion of virtual PortChannel (vPC) information in a TRansparent Interconnect of Lots of Links network environment, deriving, from the portion of vPC information, a physical nickname of an edge switch to which a frame can be forwarded, and rewriting an egress nickname in a TRILL header of the frame with the physical nickname. In example embodiments, the vPC information can include respective vPC virtual nicknames, EtherChannel hash algorithms, hash values, and physical nicknames of edge switches associated with vPCs in the network environment. In some embodiments, the portion of vPC information can be derived from an Interested vPC Type Length Value (TLV) information of an Intermediate System to Intermediate System (IS-IS) routing protocol data unit (PDU).

Abstract: In one embodiment, one or more indicia of stress are monitored. Based on the one or more indicia of stress, it is determined a stress condition exists. In response to the stress condition, one or more link aggregation actors and partners are caused to enter a grace state for a grace period. While the one or more link aggregation actors and partners are in the grace state, link aggregation formation is paced on a plurality of links by delaying formation of one or more new link aggregation groups on the plurality of links until a hold is released. Upon expiration of the grace period, the grace state is exited.

Abstract: In one embodiment, a period between periodic transmissions of protocol data units (PDUs) used to form or maintain a link aggregation group is initially set to a fixed value. When a stress condition is detected, the period between periodic transmissions of PDUs is increased from the initial value. When the stress condition is determined to have eased, the period between periodic transmissions of PDUs is reduced back toward the fixed value.

Abstract: Synchronization of traffic multiplexing in link aggregation is described. In an embodiment, a first link aggregator and a second link aggregator are associated with a plurality of links. The first link aggregator maintains an identifier for each link indicating at least a state of enabled or disabled. A synchronized clock is established between the first link aggregator and the second link aggregator. A particular link of the plurality of links is transitioned. Wherein, the transitioning is performed by the first link aggregator sending, to the second link aggregator, a first message identifying a particular time to transition the particular link. The first link aggregator receives, from the second link aggregator, a second message indicating that the particular time is acceptable. In response to a determination that the second message indicates that the particular time is acceptable and that the synchronized clock has reached the particular time, transitioning the link.

Abstract: In one embodiment, a layer-2 network that includes a cloud switch is partitioned into a plurality of segments, each segment including one or more cloud switch domains that are coupled via a logical port to a corresponding one of a plurality of internal logical shared media links. One of the internal logical shared media links is provisioned as a hub. One or more remaining internal logical shared media links are defaulted to be spokes. A spanning tree protocol (STP) is executed within each segment. The logical port of each cloud switch domain advertises a pseudo root bridge identifier (ID) to cause the internal logical shared media link to appear attached to a Root. The advertised pseudo root bridge ID of the hub is chosen to have a higher priority than the pseudo root bridge ID of the spokes to establish a hub and spoke relationship among the segments.

Abstract: In one embodiment, a method includes detecting a change in network topology and broadcasting a transient unconditional unpruning message to all nodes in the network. The message is configured to instruct each network element 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.

Abstract: In one embodiment, a multiple spanning tree (MST) region is defined in a network, where the MST region includes a plurality of network nodes interconnected by links. A MST cluster is defined within the MST region, where the MST cluster includes a plurality of network nodes selected from the plurality of network nodes of the MST region. A network node of the MST cluster generates one or more MST bridge protocol data units (BPDUs) that present the MST cluster as a single logical entity to network nodes of the MST region that are not included in the MST cluster, yet enables per-multiple spanning tree instance (per-MSTI) load balancing of traffic across inter-cluster links that connect network nodes included in the MST cluster and network nodes of the MST region that are not included in the MST cluster.

Abstract: In one embodiment, bridges in a computer network maintain a per-port mapping table for each of its ports, where each mapping table maps, for each virtual connection (of more than 4K) at a respective port, i) frame encapsulation fields that uniquely identify a particular virtual connection at the respective port to ii) a particular multiple spanning tree (MST) instance. The bridges may then compute a checksum of a particular mapping table for a particular port, and share the checksum with a corresponding port interconnected with the particular port (e.g., of another bridge). Upon determining that the mapping tables at the corresponding ports match in response to the checksums matching, frames may then be forwarded between the ports based on the particular mapping table.