A Media Access Control address (MAC) learning method includes: parsing out packet header and packet verification parameter of a packet from an input/output port; generating a port identifier corresponding to the input/output port; starting first-stage procedure for the packet header; and starting second-stage procedure for the packet verification parameter. The first-stage procedure includes: performing, according to a MAC forwarding table and the port identifier, learning processing for source MAC address of the packet header to generate learning result; generating status parameter according to the learning result; and associating and storing the status parameter, the port identifier, and a hash address corresponding to the source MAC address into a memory. The second-stage procedure includes: obtaining the status parameter and the hash address from the memory according to the port identifier; and updating the MAC forwarding table according to the packet verification parameter, the obtained status parameter, and the obtained hash address.

In order to enable dynamic scaling of network services at the edge, novel systems and methods are provided to enable addition of add new nodes or removal of existing nodes while retaining the affinity of the flows through the stateful services. The methods provide a cluster of network nodes that can be dynamically resized to handle and process network traffic that utilizes stateful network services. The existing traffic flows through the edge continue to function during and after the changes to membership of the cluster. All nodes in the cluster operate in active-active mode, i.e., they are receiving and processing traffic flows, thereby maximizing the utilization of the available processing power.

In order to enable dynamic scaling of network services at the edge, novel systems and methods are provided to enable addition of add new nodes or removal of existing nodes while retaining the affinity of the flows through the stateful services. The methods provide a cluster of network nodes that can be dynamically resized to handle and process network traffic that utilizes stateful network services. The existing traffic flows through the edge continue to function during and after the changes to membership of the cluster. All nodes in the cluster operate in active-active mode, i.e., they are receiving and processing traffic flows, thereby maximizing the utilization of the available processing power.

Embodiments of this application disclose a method for discovering a forwarding path and a related device thereof, to discover a forwarding path. The method includes: receiving, by a first device, a packet that is sent by a second device and that is used to discover a forwarding path; searching, by the first device based on a first forwarding entry of a data plane, for forwarding information used to forward the packet; and sending, by the first device, path information to the second device based on a second forwarding entry of an autonomic control plane virtual routing and forwarding (ACP VRF) instance, where the first forwarding entry and the second forwarding entry are isolated from each other. In the embodiments, the first forwarding entry and the second forwarding entry are isolated from each other, and returning of the path information is not affected by a data plane fault.

A network configuration apparatus configures a closed network constructed independently for each user in an open network as a cloud LAN, generates an access point for accessing the cloud LAN assigned to each of a plurality of terminals that belong to a user using the cloud LAN. A user information management apparatus selects an access point assigned to a connection terminal accessing the cloud LAN via a mobile data transfer network, and notifies the connection terminal of the access point selected. An address management apparatus delivers an address for the connection terminal to access the cloud LAN in response to a request from the connection terminal.

Introduced here are approaches to classifying traffic that comprises data packets. For each data packet, a classification engine implemented on a computing device can identify an appropriate class from amongst multiple classes using a lookup table implemented in a memory. The memory could be, for example, static random-access memory (SRAM) as further discussed below. Moreover, the classification engine may associate an identifier with each data packet that specifies the class into which the data packet has been assigned. For example, each data packet could have an identifier appended thereto (e.g., in the form of metadata). Then, the data packets can be placed into queues based on the identifiers. Each queue may be associated with a different identifier (and thus a different class).

To realize a low power consumption and a small area of a network communication system and a semiconductor device for mounting the same. In the processing method of the network router or network communication frame, the received frame is input to the hash generator, to obtain an address based on the resulting hash value, the position of the address in the rule table, stores the rule corresponding to the received frame.

To realize a low power consumption and a small area of a network communication system and a semiconductor device for mounting the same. In the processing method of the network router or network communication frame, the received frame is input to the hash generator, to obtain an address based on the resulting hash value, the position of the address in the rule table, stores the rule corresponding to the received frame.

This application relates to the field of communication technologies, and discloses a method and an apparatus for determining a link for forwarding a service flow, and a storage medium. In embodiments of this application, a first forwarding device may obtain identification information of a first service flow; and determine, based on the identification information of the first service flow, a link bandwidth matrix, and link statuses respectively corresponding to N links, a first link for forwarding the first service flow. It can be learned that in embodiments of this application, a hash operation does not need to be performed based on a device identifier of each forwarding device, and a specific forwarding device that performs forwarding does not need to be determined by comparing a plurality of hash values. Therefore, an amount of calculation is small and efficiency is high.

A method includes identifying a plurality of local tracklets from a plurality of targets, creating a plurality of global tracklets from the plurality of local tracklets, wherein each global tracklet comprises a set of local tracklet of the plurality of local tracklets, wherein the set of local tracklet corresponds to a target of the plurality of targets; extracting motion features of the target from the each global tracklet of the plurality of global tracklets, wherein the motion features of each target of the plurality of targets from each global tracklet of the plurality of global tracklets are distinguishable from the motion features of remaining targets of the plurality of targets from remaining global tracklets; transforming the motion features into an address code by using a hashing process; and transmitting a plurality of address codes and a transformation parameter of the hashing process to a communication device.