A network interface of a first computing device is configured to operate according to a bridge table. The bridge table defines a spanning tree protocol for a mesh network and identifies one or more reachable nodes. A communication characteristic between the first computing device and a second computing device of the one or more reachable nodes is determined to exceed a quality threshold. Based on the determination that the communication characteristic exceeds the quality threshold, the spanning tree protocol is overridden and the data is transmitted directly to the second computing device via a direct communication route.

The disclosed computer-implemented method may include (1) receiving, at a network device, a route update for one or more routes that direct traffic within a network that supports BGP, (2) identifying, within the route update, a BGP prefix and a plurality of protocol next-hop addresses that (A) identify a plurality of neighbors of the network device and (B) each correspond to the BGP prefix, (3) maintaining a single copy of the BGP prefix and each of the protocol next-hop addresses, (4) receiving a packet destined for a computing device that is reachable via at least one of the neighbors of the network device, and then (5) forwarding the packet to the one of the neighbors of the network device in accordance with the BGP prefix and the protocol next-hop address that identifies the one of the neighbors. Various other methods, systems, and apparatuses are also disclosed.

In an embodiment of the invention, a system determines connections between source and target nodes in a network by determining edges with common nodes between the source and target nodes within the network for each of one or more hops. Each determined edge links a pair of nodes in a network path between the source and target nodes. The system removes certain edges from the determined edges to produce a resulting set of edges. In particular, each removed edge is an edge that includes a node within a loop in the network or is an edge that is unconnected to another edge. The system determines connections between the source and target nodes based on the resulting set of edges. Embodiments of the present invention further include a method and computer program product for determining connections between source and target nodes in a network in substantially the same manners described above.

An apparatus includes a network interface and a processor. The network interface is configured to communicate with a network that includes a plurality of switches interconnected in a Cartesian topology having multiple dimensions. The processor is configured to predefine an order among the dimensions of the Cartesian topology, to search for a preferred route via the network from a source switch to a destination switch, by evaluating candidate routes based at least on respective numbers of switches along the candidate routes for which traversal to a next-hop switch changes from one of the dimensions to another of the dimensions opposite to the predefined order, and to configure one or more of the switches in the network to route packets from the source switch to the destination switch along the preferred route.

Access-side loop mitigation may be provided. First, a first edge device may determine that a duplicate host exists on a network. Then the first edge device may detect a loop in response to determining that the duplicate host exists on the network. Detecting the loop may comprise sending a message on a plurality of access-side ports of the first edge device and then receiving, in response to sending the message on the plurality of access-side ports of the first edge device, a response on a first access-side port of the plurality of access-side ports of the first edge device. Next, the first edge device may mitigate the detected loop in response to receiving the response.

A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions that are executed by the at least one processor and configure the at least one processor to implement a path query cache. Responsive to receiving a path query from a process executing in the data processing system, the path query cache performs a lookup of the path query in the path query cache. The path query identifies a source port, a source address and a destination address. The path query cache stores a plurality of entries, each entry comprising a source port, a source address, a destination address, the source and destination global identifiers, and good/bad flag indicating whether a path associated with the entry is available or not. Responsive to the path query cache determining the path query matches a valid entry in the plurality of entries, the path query cache returns a result to the process. The result comprises the source and destination global identifiers and the good/bad flag from the valid entry.

In an embodiment of the invention, a system determines connections between source and target nodes in a network by determining edges with common nodes between the source and target nodes within the network for each of one or more hops. Each determined edge links a pair of nodes in a network path between the source and target nodes. The system removes certain edges from the determined edges to produce a resulting set of edges. In particular, each removed edge is an edge that includes a node within a loop in the network or is an edge that is unconnected to another edge. The system determines connections between the source and target nodes based on the resulting set of edges. Embodiments of the present invention further include a method and computer program product for determining connections between source and target nodes in a network in substantially the same manners described above.

In an embodiment of the invention, a system determines connections between source and target nodes in a network by determining edges with common nodes between the source and target nodes within the network for each of one or more hops. Each determined edge links a pair of nodes in a network path between the source and target nodes. The system removes certain edges from the determined edges to produce a resulting set of edges. In particular, each removed edge is an edge that includes a node within a loop in the network or is an edge that is unconnected to another edge. The system determines connections between the source and target nodes based on the resulting set of edges. Embodiments of the present invention further include a method and computer program product for determining connections between source and target nodes in a network in substantially the same manners described above.

A data packet transmission method and a border routing bridge device, where the method includes receiving, by a first border routing bridge device of a first area, a first data packet sent by a border routing bridge device of a second area to the first area, determining, a device identifier group of the second area according to the first data packet, determining, from the device identifier group of the second area, according to the first data packet, a device identifier of a border routing bridge device used to forward a return data packet sent by the target device to the source device, and sending, by the first border routing bridge device, a second data packet carrying the determined device identifier to the target device, where the determined device identifier is used as a source routing bridge device identifier of the second data packet.

An inter-cloud communication method, used to implement communication between two clouds, where virtual machines belonging to a same virtual network are created in the two clouds. A receive end cloud uses a gateway node as an entrance to external communication, and all data packets to be sent to a virtual machine in the receive end cloud are sent to the gateway node, thereby preventing a location change of the virtual machine from affecting a transmit end cloud. In addition, the data packet only needs to pass through the gateway node in the receive end cloud and a computing node on which the virtual machine that receives the data packet is located, that is, the data packet only needs two hops to reach a destination, thereby shortening a communication path, and improving inter-cloud communication efficiency.