Technologies for scalable local addressing 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 DLID may be 32, 24, 20, or 16 bits wide. The managed network device may determine whether the DLID is within a configurable multicast address space and, if so, forward the data packet to a multicast group. The managed network device may also determine whether the DLID is within a configurable collective address space and, if so, perform a collective acceleration operation. The number of top-most bits set in a multicast mask and the number of additional top-most bits set in a collective mask may be configured. Multicast LIDs may be converted between different bit lengths. Other embodiments are described and claimed.

Technologies for fabric security include one or more managed network devices coupled to one or more computing nodes via high-speed fabric links. A managed network device enables a port and, while enabling the port, securely determines the node type of the link partner coupled to the port. If the link partner is a computing node, management access is not allowed at the port. The managed network device may allow management access at certain predefined ports, which may be connected to one of more management nodes. Management access may be allowed for additional ports in response to management messages received from the management nodes. The managed network device may check and verify data packet headers received from a compute node at each port. The managed network device may rate-limit management messages received from a compute node at each port. Other embodiments are described and claimed.

An arrangement for a wireless communication device is disclosed. The arrangement is adapted to set up an application connection between an application of an application layer of the device and a remote server. The device comprises a modem subsystem (comprising the application layer, a remote socket client and a remote socket API between the application layer and the remote socket client), an application processor (comprising a remote socket server and an IP stack, wherein the application processor is associated with a wireless communication access unit and the IP stack is adapted to connect to a communication network using the access unit), and a remote socket protocol communication channel between the remote socket client and the remote socket server. The application is adapted to send an application connection setup request to the remote socket client via the remote socket API. The remote socket client, the remote socket server and the remote socket protocol communication channel are collectively adapted to use a remote socket protocol to set up a remote socket connection between the remote socket client and the remote server via the remote socket server and via the IP stack, using the remote socket protocol communication channel and the wireless communication access unit, and to establish the application connection based on the remote socket connection. The remote socket client is further adapted to (in response to the application connection being established) send an application connection setup response to the application via the remote socket API.

An RB device creates a primary multicast tree and a corresponding backup multicast tree, and determines whether the primary multicast tree for forwarding traffic fails or not, according to a received first LSP packet; when the primary multicast tree fails, the RB device forwards the traffic using the backup multicast tree.

A gateway provides duplex-directional, multimedia ad hoc mesh networking, peer-to-peer direct communications, power optimization, dynamic configuration, and data management, while operating within various devices and network topologies. A multitasking virtual machine monitor for mobile networked devices, that is capable of functional expandability and portability to various operating environments, interoperability with a variety of operating systems, the Gateway Control System (GCS) performs functional capabilities in both a local and a networked topology using local and remote hardware and software. Software within the GCS is partitioned into sequentially, autonomous code, referred to herein as “modules,” each module being configured to communicate with hardware and other gateway modules. Collectively, all gateway modules are referred to herein as the gateway stack (GS). Each member of the GS can be turned on or off, downloaded from a remote site, and dynamically configured.

A method and system for transmitting and receiving data packets between two network nodes via one or more end-to-end connections. An interface is provided for selecting one or more possible end-to-end connection(s) or established end-to-end connection(s). The method and system may further comprise receiving a policy, wherein one or more selected end-to-end connections are established based, at least in part, on the policy. The policy may also restrict or promote selection of certain established end-to-end connection(s) via the interface provided. The selected and established end-to-end connection(s) are used for transmitting and receiving data packets.

The present invention relates to a traffic distribution method, apparatus, and system. The method includes: receiving a current packet sent by a first entity; acquiring layer 7 application information according to the current packet; if the layer 7 application information is acquired, matching the current packet with a layer 7 traffic distribution policy according to the layer 7 application information; and sending the current packet to a service server after the current packet matches the layer 7 traffic distribution policy. In this way, the present invention implements traffic distribution based on the layer 7 application information, enhances performance of a traffic distribution device, and reduces deployment costs of an operator.

In the field of network communications, a protection method for a multi-domain network includes: after a second node detects that a first link fails, disconnecting a first protection path on the node, connecting a first sub-path and a path that is within a second domain, uses the second node as an endpoint, and is used to bear a service; sending, on the first sub-path, a first failure monitoring message that carries first maintenance information to a third node, where the first maintenance information is the same as second maintenance information carried in a second failure monitoring message; the second failure monitoring message is a message that is sent on the first protection path by a first node to the third node and is used to monitor a failure of the first protection path.

The present invention discloses a data switching apparatus and system, where the data switching apparatus includes: an optical-to-electrical conversion unit, an identification unit, an electrical switching unit, an electrical-to-optical conversion unit, an optical switching control unit, and an optical switching unit. The optical-to-electrical conversion unit is configured to perform optical-to-electrical conversion on a first optical data packet and an optical label, where the optical label carries switching information of a second optical data packet, and the first optical data packet and the second optical data packet are respectively to-be-switched data packets that need to use electrical packet switching and optical packet switching. The identification unit is configured to identify whether an electrical signal output by the optical-to-electrical conversion unit is from the optical label or the first optical data packet.

Arrangements and methods for improving data communication in a network are disclosed. The method includes receiving data packets and segregating the data packets into at least original packets and replicated packets. The method also includes prioritizing original packets having service level agreement (SLA) requirements, the prioritizing is performed with respect to at least one of queuing and de-queuing such that SL parameters for the original packets met.