Implementations of discovery functionalities in accordance with the present invention are characterized by being exceptionally minimalistic. A primary reason and benefit for such minimalistic implementations relate to these discovery functionalities being implemented via a management processor and associated resources of a system on a chip (SoC) unit as opposed to them being implemented on data processing components of a cluster of nodes (i.e., central processing core components). By focusing on such a minimalist implementation, embodiments of the present invention allow discovery functionalities to be implemented on a relatively low-cost low-power management processor coupled to processing cores that provide for data serving functionality in the cluster of nodes.

Embodiments of the present invention include systems and methods for identifying a primary flow and its corresponding subflow(s) so that the subflow(s) may be routed to more efficiently use bandwidth between a source host and a destination host. In embodiments, a table correlates flows and their corresponding keys for Multipath TCP flows. When a new subflow is initiated between a source device and a destination device, the new flow can be identified as being a subflow of a primary flow using data in the table. Having identified the subflow and its corresponding primary flow, the new subflow may have an installed route path that differs from its primary flow, thereby improving the bandwidth usage.

A capability for cross-layer aware communication of a multipath data flow via a communication network is presented. The multipath data flow is transported using a set of multiple transmission flows based on a multipath transport protocol. The communication network supports a set of multiple communication paths. A controller is configured to determine a set of mappings between the multiple transmission flows of the multipath data flow and the multiple communication paths based on cross-layer state information, compute a set of path mapping rules for a network element based on the mappings between the multiple transmission flows of the multipath data flow and the multiple communication paths, and provide the path mapping rules to the network element. The network element is configured to apply the path mapping rules for mapping packets of the multipath data flow between the multiple transmission flows of the multipath data flow and the multiple communication paths.

Techniques for performing efficient topology failure detection in SDN networks are provided. In one embodiment, a computer system (e.g., an SDN controller) can transmit a first message to a first network device, where the first message instructs the first network device to begin sending probe packets to a second network device at a predetermined rate. The computer system can further transmit a second message to the second network device, where the second message instructs the second network device to monitor for the probe packets sent by the first network device and to notify the computer system when one or more of the probe packets are not received by the second network device. If the computer system receives such a notification from the second network device, the computer system can determine that a port, link, or node failure has occurred between the first and second network devices.

In an example, a computer-readable medium may store executable instructions. The executable instructions may be to detect an inoperative network device in a communication network managed by a controller, determine a network switching function assigned to the inoperative network device, and provide the network switching function through the controller itself instead of the inoperative network device.

In one aspect, a computerized system useful for implementing a cloud-based multipath routing protocol to an Internet endpoint includes an edge device that provides an entry point into an entity's core network. The entity's core network includes a set of resources to be reliably accessed. The computerized system includes a cloud-edge device instantiated in a public-cloud computing platform. The cloud-edge device joins a same virtual routing and forwarding table as the edge device. The cloud-edge device receives a set of sources and destinations of network traffic that are permitted to access the edge device and the set of resources.

The invention relates to a method for generating a load sharing vector indicating a plurality of communication targets for load sharing in a communication network. The method comprises providing a target distribution vector comprising a first number of entries indicating a first communication target, and comprising a second number of entries indicating a second communication target, and generating the load sharing vector upon the basis of active entries of the target distribution vector, the active entries indicating the communication target of the first or the second communication target which is available for load sharing in the communication network.

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.

A method performed by a network node. The method includes detecting a loss of connection at an incoming interface to an upstream neighbor of the network node, where the network node is in a multicast communication network that includes a multicast tree to provide connectivity from a common source node to one or more multicast recipient nodes. The multicast communication network further includes a set of one or more secondary paths to provide redundancy to the multicast tree, and sending a notification packet downstream toward the one or more multicast recipient nodes when the network node cannot re-route the multicast data traffic to allow the multicast data traffic to be received by the multicast recipient nodes, wherein the notification packet causes one or more downstream nodes to switch multicast reception to one or more of the set of one or more secondary paths to re-route the multicast data traffic.

Techniques are described for providing managed computer networks. In some situations, the techniques include managing communications for computing nodes of a managed computer network by using one or more particular computing nodes of the managed computer network that are configured to operate as intermediate destinations to handle at least some communications that are sent by and/or directed to one or more other computing nodes of the managed computer network. In addition, the techniques may include managing the communications in accordance with configured failure behavior specified for one or more computing nodes of the computer network, such as specified failure behavior for a computing node configured to operate as an intermediate destination that indicates how communications that would otherwise be routed via the intermediate destination computing node are to be handled if the intermediate destination computing node fails or is otherwise unavailable (e.g., to block or allow such communications).