In a domain name system (DNS) server allocation method, a session management function (SMF) receives a session establishment request message sent by UE, where the request message includes a name of a data network to be accessed by the UE. The SMF obtains an IP address of a first DNS server based on the name of the data network and a geographical location of the UE. The SMF then sends to the UE a session establishment response message that includes the IP address of the first DNS server.

In a domain name system (DNS) server allocation method, a session management function (SMF) receives a session establishment request message sent by UE, where the request message includes a name of a data network to be accessed by the UE. The SMF obtains an IP address of a first DNS server based on the name of the data network and a geographical location of the UE. The SMF then sends to the UE a session establishment response message that includes the IP address of the first DNS server.

Various embodiments of the teachings herein include a network topology construction method. The method may include: acquiring a MAC address table of each port on each switch in a target network; determining a first connection relationship in the target network according to the MAC addresses of terminal devices in the target network included in each acquired MAC address table; determining at least one first port according to the first connection relationship in the target network; determining a second connection relationship in the target network according to the MAC addresses included in the MAC address table of each of the first ports in the target network; and determining a network topology of the target network according to the first connection relationship and the second connection relationship in the target network.

Various embodiments of the teachings herein include a network topology construction method. The method may include: acquiring a MAC address table of each port on each switch in a target network; determining a first connection relationship in the target network according to the MAC addresses of terminal devices in the target network included in each acquired MAC address table; determining at least one first port according to the first connection relationship in the target network; determining a second connection relationship in the target network according to the MAC addresses included in the MAC address table of each of the first ports in the target network; and determining a network topology of the target network according to the first connection relationship and the second connection relationship in the target network.

Examples include a computing system having a plurality of processing cores and a memory coupled to the plurality of processing cores. The memory has instructions stored thereon that, in response to execution by a selected one of the plurality of processing cores, cause the following actions. The selected processing core to receive a packet and get an original tuple from the packet. When no state information for a packet flow of the packet exists in a state table, select a new network address as a new source address for the packet, get a reverse tuple for a reverse direction, select a port for the packet from an entry in a mapping table based on a hash procedure using the reverse tuple, and save the new network address and selected port. Translate the packet's network address and port and transmit the packet.

Embodiments described herein generally involve identifying workloads in a multi-site networking environment. Embodiments include determining that a given network is stretched across a first network segment at a first site and a second network segment at a second site. Embodiments include creating a stretched administrative domain for the given network and mapping an address of the given network to the stretched administrative domain in a lookup table for an administrative domain associated with the first network segment. Embodiments include receiving a flow record from an observation point in the first network segment, the flow record having a source IP address associated with the second network segment and a destination IP address associated with the first network segment. Embodiments include identifying a source workload and destination workload of the flow record using the lookup table and a workload identification table that maps combinations of IP addresses and administrative domains to workloads.

One aspect provides a method and system for managing address resolution requests in a network. During operation, a gateway of the network advertises a route for sending address resolution requests and determines whether a cached entry corresponding to an address resolution request received via the route exists in a neighbor table. In response to determining that the cached entry exists, the gateway responds to the address resolution request based on the cached entry; in response to determining that the cached entry does not exist, the gateway replicates the address resolution request to edge devices in the network, thereby facilitating discovery of a target host corresponding to the address resolution request.

Some embodiments establish for an entity a virtual network over several public clouds of several public cloud providers and/or in several regions. In some embodiments, the virtual network is an overlay network that spans across several public clouds to interconnect one or more private networks (e.g., networks within branches, divisions, departments of the entity or their associated datacenters), mobile users, and SaaS (Software as a Service) provider machines, and other web applications of the entity. The virtual network in some embodiments can be configured to optimize the routing of the entity's data messages to their destinations for best end-to-end performance, reliability and security, while trying to minimize the routing of this traffic through the Internet. Also, the virtual network in some embodiments can be configured to optimize the layer 4 processing of the data message flows passing through the network.

Some embodiments establish for an entity a virtual network over several public clouds of several public cloud providers and/or in several regions. In some embodiments, the virtual network is an overlay network that spans across several public clouds to interconnect one or more private networks (e.g., networks within branches, divisions, departments of the entity or their associated datacenters), mobile users, and SaaS (Software as a Service) provider machines, and other web applications of the entity. The virtual network in some embodiments can be configured to optimize the routing of the entity's data messages to their destinations for best end-to-end performance, reliability and security, while trying to minimize the routing of this traffic through the Internet. Also, the virtual network in some embodiments can be configured to optimize the layer 4 processing of the data message flows passing through the network.

Embodiments of this application disclose a method, an apparatus, and a system for implementing data transmission. The method includes: obtaining, by a sending device, a data packet in a target data flow; and sending the data packet through each of at least two physical links between the sending device and a receiving device, where the data packet sent through each of the at least two physical links includes a same sequence number. Because the data packet in the target data flow is sent through different physical links, not through only one physical link, when a transmission latency of the data packet is increased due to a bandwidth instability factor such as burst traffic or electromagnetic wave interference on any physical link, the receiving device can combine, into a target video flow, data packets that are sent through other physical links and that have a lower latency.