A method is described for serial data transmission in a bus system having at least two participating data processing units, the data processing units exchanging messages via the bus, the sent messages having a logical structure in accordance with CAN standard ISO 11898-1. When a first changeover condition is present, then, deviating from CAN, the data field of the messages can include more than eight bytes, the values of the data length code being interpreted, given the presence of the first changeover condition to determine the size of the data field. For forwarding data between the data field and the application software, at least one buffer memory is provided, and, if the size of the data field differs from the size of the buffer memory used, the forwarded quantity of data is adapted at least corresponding to the difference in size between the data field and the buffer memory.

A packet processing block. The block has an input for receiving data in a packet header vector, the vector comprising data representing information for a packet and a match unit for performing match operations between packet header vector data and at least one match table. Various embodiments provide advantages in connection with storing certain action or next table bits outside of the match table, or constants in the table, or by forming the match table from multiple unit match table memories.

Service function chaining is a sequence of service function instances that traffic flows need to traverse through in order. Those service function instances are not required to reside on the direct path and traffic flow, but steered through network nodes. Service function instances and network nodes process the packets that carry a service function chain (SFC) header. The packets are encapsulated by a virtual network overlay header and forwarded through the service function instances in an SFC. The SFC header in specific format will prompt the network nodes to re-route the packets in the traffic flow using destination based forwarding or path based forwarding method in the packet network as well as an SDN controller and/or in-band control plane, and able to carry the metadata with the packets.

A method for a host machine that hosts at least one tenant virtual machine (VM) of a particular tenant logical network that accesses service VMs of a particular service logical network. The method, prior to a packet being received at a PFE on the host, intercepts the packet that sent by the tenant VM to one of the service VMs based on a set of forwarding rules. The packet includes a source IP address and a source port number of the tenant VM. The method, prior to the packet leaving the PFE in the host, replaces the source IP address and source port number with a replacement IP address and port number pair from a set of replacement IP address and port number pairs allocated to the host for accessing service VMs. The method sends the modified packet to the PFE to forward the modified packet to the service VM.

In a forwarding network comprising a function chain network controller, a plurality of intermediate network functions (NFs) and flow-based chain selectors (FBCSs) forming VNFs and configured to transfer data packets via a plurality of links, a method comprising a FBCS requesting substitution in the header representation of function chain entries of a data packet header in a flow with a different representation of function chain entries, wherein the flow bypasses at least one intermediate FBCS based on the substituted function chain entries representation. The function chain network controller discovers FBCS capable nodes and their topology, and maintains a function chain substitution state and distributes it to the FBCS relevant substitutions. The function chain network controller distributes a list of adjacent FBCSs to the FBCS, and distributes a list of abstracted adjacent FBCSs to the FBCS and translates requests from an abstracted value to a real value.

Technologies for medium grained adaptive routing include one or more managed network devices coupled to one or more computing nodes via high-speed fabric links. A computing node may transmit a data packet including a destination local identifier (DLID) that identifies the destination computing node. The managed network device determines a static destination port based on the DLID, and determines whether the static destination port is congested. If congested, the managed network device determines a port group based on the DLID and selects a dynamic destination port from the port group. The port group may include two or more destination ports of the managed network device, and port groups may overlap. Port groups may be described by port masks stored in a port group table. The port groups and mappings between DLIDs and port groups may be configured by a fabric manager. Other embodiments are described and claimed.

Exemplary payment networks and methods are provided for facilitating data transfers. One exemplary method includes determining a subset of network routers that offer access to a regional hub based on network address summaries for first and second routers and prioritizing the first router over the second router, based on a specificity value of each of the first and second routers, as defined by the network address summaries. The method also includes checking whether a connection to the first router provides a viable data transfer path to the regional hub and recording the path to the first router in a routing table, when the connection to the first router is viable. Further, the method includes receiving a request to transfer data to the regional hub and transferring the data, via the path recorded in the routing table, to the regional hub.

Aspects of the embodiments are directed to augmenting a control packet with an interface identifier, the interface identifier identifying an interface at a physical network forwarding element; and transmitting the control packet with the interface identifier to the physical network forwarding element. The interface identifier can be included in metadata of a network service header (NSH). The NSH is encapsulated with the control packet, which is transmitted with the control packet. The NSH can be extracted and the interface identifier used to identify a user interface (or a presenting interface) based on a metadata lookup.

In an approach for achieving resilience and load balancing control over layer 2 gateways in a cluster, a processor forms a cluster, wherein the cluster includes one or more layer 2 gateways. A processor registers endpoints for a tenant system attached to a virtual network through a bridge network to add to an endpoint database used to associate a destination MAC address with the cluster. A processor distributes flow of data.

A method of addressing IoT device and applying such for IoT connection adopts a design of global IoT addresses with a hierarchical structure and installs a virtual communication protocol into a physical communication protocol equivalent to the position of an application layer (Layer 7) of an OSI model, so that the virtual communication protocol is operated with the physical communication protocol online to allow two IoT devices with different physical communication protocols to communicate and transmit control commands with each other on an IOT with a hierarchical tree structure and achieve the communication between IoT devices in a quick and low-cost manner.