Abstract: A first VXLAN Tunnel End Point (VTEP) determines a simulation packet for simulating a service forwarding path of a service packet forwarded from a first Virtual Machine (VM) accessing the first VTEP to a second VM accessing a second VTEP when the service packet sent by the first VM does not reach the second VM. A packet character parameter of the simulation packet is the same as a packet character parameter of the service packet. The first VTEP calculates the packet character parameter of the simulation packet to determine a User Datagram Protocol (UDP) source port number, performs VXLAN encapsulation for the simulation packet according to the determined UDP source port number and a VXLAN tunnel identity in a local register entry matching with the simulation packet, and forwards the simulation packet with the VXLAN encapsulation via a VXLAN tunnel corresponding to the VXLAN tunnel identity.

Abstract: Examples of the present disclosure provide a VM packet controlling method and apparatus, applicable for an OpenStack network. The OpenStack network includes an OpenStack controller node, an OpenStack compute node, and a virtual network system. The OpenStack network is communicatively connected with an SDN controller, the virtual network system includes a VM and a virtual network apparatus responsible for forwarding packets of the virtual machine. The OpenStack controller node creates a port for the VM, informs the SDN controller of a port UUID and a forwarding rule applied on the port; the OpenStack controller node receives a port ID, and transmits a corresponding relationship between the port ID and the port UUID to the SDN controller, the SDN controller generates a flow table according to the forwarding rule applied on the port, and issues the flow table to the virtual network apparatus according to the corresponding relationship.

Abstract: A SDN controller obtains and stores a NAT mapping relationship between a private network address and a public network of a host computer in each SDN; receives a flow table request for a data packet from a VTEP device, searching for a NAT mapping relationship corresponding to a target IP address of the data packet when determining that the data packet is forwarded across SDNs; generates a flow table used for forwarding the data packet according to the NAT mapping relationship corresponding to the target IP address searched out and network topology information, and transmits the flow table to the VTEP device, wherein the flow table comprises a NAT processing instruction for a source IP address and encapsulation information, and a target IP address in the encapsulation information is a public network address in the NAT mapping relationship searched out.

Abstract: A Multibit Trie is created for routing distribution of IP prefixes in each Virtual Private Network (VPN). Routing of IP prefixes in the highest level 1˜m of the Multibit Trie is expanded to IP prefixes in level m+1 according to a prefix expansion method, wherein m is an integer larger than 1. Each branch of the IP prefixes in the level m+1 of the Multibit Trie is taken as a Branch_Tree, and data structure information of each Branch_Tree is saved. When routing of an IP address in a VPN is to be searched, a Branch_Tree is searched in a Multibit Trie corresponding to the VPN according to the highest m+1 bits of the IP address, and the routing of the IP address is searched in the Branch_Tree.

Abstract: A method and device for realizing automatic stacking of network devices are disclosed. According to an example of the method, when a network device determines its device role, the network device may send a first neighbor discovery message to a neighbor device and receive a second neighbor discovery message sent by the neighbor device. Next, if it determines that a topological structure between the network device and the neighbor device changes according to the second neighbor discovery message, the network device may determine whether a stacking condition to trigger stacking the network device and the neighbor device is satisfied or not. If the stacking condition is satisfied, the network device may further determine a stacking configuration for stacking the network device and the neighbor device. Then the network device may stack the network device with the neighbor device according to the stacking configuration.

Abstract: A method of forwarding a packet and a network device are provided. According to an example of the method, when serving as a previous-hop device of a destination device of a first tunnel, the network device receives a first notification message from the destination device of the first tunnel, where information relating the first tunnel is carried in the first notification message. The network device configures a forwarding entry, where a match domain of the forwarding entry includes the information relating the first tunnel. After an encapsulated data packet is received, and if the encapsulated data packet matches the forwarding entry, the network device decapsulates the encapsulated data packet and then forwards the decapsulated data packet to the destination device of the first tunnel.

Abstract: A network device may include a first forwarding board, a second forwarding board and an interface board. The interface board may include a control apparatus and a network interface chip. The control apparatus may form a first upstream packet flow which is sent to the first forwarding board via a first I/O bus and a second upstream packet flow which is sent to the second forwarding board via a second I/O bus using data packets received through the network interface chip from the exterior of the network device.

Abstract: When a first interface board receives from an Ethernet switch chip a first Ethernet data packet, once a destination board of the data packet is determined as second interface board logical device of the first interface board encapsulates the data packet into a PCI-E packet that takes a PCI-E memory space address of a board memory in the second interface board as a destination address, so as to enable a PCI-E Endpoint to forward the first PCI-E packet to a forwarding board of a network device; when the first interface board obtains from a board memory a second PCI-E packet coming from a third interface board, logical device of the first interface board parses out a Ethernet data packet from the second PCI-E packet, and transmits the data packet to the Ethernet switch chip, the third interface board and second interface board being the same or not same.

Abstract: An I/O board of a VXLAN switch receives a multicast data packet having a first VXLAN encapsulation, removes the first VXLAN encapsulation, determines that layer 3 multicast forwarding is to be performed for the multicast data packet, and sends the multicast data packet to a fabric board. The fabric board determines that layer 3 multicast forwarding is to be performed for the multicast data packet. When a multicast group member port corresponding to the multicast data packet is a VXLAN tunnel port, the fabric board modifies a source MAC address of the multicast data packet and sends the modified multicast data packet to an I/O board corresponding to the multicast group member port. The I/O board corresponding to the multicast group member port adds a second VXLAN encapsulation to the multicast data packet and forwards the multicast data packet having the second VXLAN encapsulation to a VXLAN.

Abstract: A line card of a virtual extensible local area network (VXLAN) gateway receives a data packet, determines to perform a layer-three forwarding to the data packet, takes a fabric board of a category as a destination fabric board, which matches with a value of a set bit position of a destination internet protocol (IP) address of the data packet, and transmits the data packet to the destination fabric board. Subsequently, after receiving the data packet, when determining to perform the layer-three forwarding to the data packet, the destination fabric board searches in address resolution protocol (ARP) entries stored therein for an ARP entry, which matches with the destination IP address of the data packet, and cooperates with a first destination line card associated with the output port in the ARP entry searched out to forward the data packet.

Abstract: An I/O board of a VXLAN switch receives a multicast data packet having a VXLAN encapsulation, removes the VXLAN encapsulation, determines that layer 3 multicast forwarding is to be performed for the multicast data packet, and sends the multicast data packet to a fabric board of the VXLAN switch. The fabric board determines that layer 3 multicast forwarding is to be performed by the fabric board for the multicast data packet. When a multicast group member port corresponding to the multicast data packet is a VLAN port, the fabric board sends the multicast data packet to each I/O board on the VXLAN switch. Each I/O board sends the received multicast data packet to a VLAN according to a layer 3 multicast group entry used for forwarding the received multicast data packet. The layer 3 multicast group entry being included in a local layer 3 multicast group table.

Abstract: I/O board of VXLAN switch removes first VXLAN encapsulation from a packet, determines to perform layer 3 forwarding for the packet and sends the packet to a fabric board of the VXLAN switch. The fabric board searches out a layer 3 entry matching a destination IP address of the packet from a local layer 3 table, modifies a source MAC address of the packet into a gateway MAC address of the VXLAN switch, modifies a destination MAC address of the packet into a destination MAC address in the layer 3 entry, and when an egress port in the layer 3 entry is a VXLAN tunnel port, sends the modified packet to an I/O board associated with the egress port in the layer 3 entry. The I/O board associated with the egress port receives the packet, adds second VXLAN encapsulation to the packet and forwards the packet to a VXLAN.

Abstract: I/O board of a VXLAN switch removes VXLAN encapsulation from a packet, determines to perform layer 3 forwarding for the packet and sends the packet to a fabric board of the VXLAN switch. The fabric board determines to perform layer 3 forwarding for the packet, searches out a layer 3 entry matching a destination IP address of the packet from a local layer 3 table, modifies a source MAC address of the packet into a gateway MAC address of the VXLAN switch, modifies a destination MAC address of the packet into a destination MAC address in the layer 3 entry, and when an egress port in the layer 3 entry is a VLAN port, sends the packet to an I/O board associated with the egress port. The I/O board associated with the egress port forwards the packet to a VLAN via the egress port in the layer 3 entry.

Abstract: An I/O board of a VXLAN switch searches out a layer 3 entry; when an egress port in the layer 3 entry is a VXLAN tunnel port, modifies a source MAC address of the packet into a gateway MAC address of the VXLAN switch, modifies a destination MAC address of the packet into a MAC address in the layer 3 entry, and sends the packet to a fabric board of the VXLAN switch. The fabric board determines to perform layer 2 forwarding for the packet, searches out a MAC entry, and when an egress port in the MAC entry is a VXLAN tunnel port, sends the packet to an I/O board associated with the egress port in the MAC entry. The I/O board associated with the egress port adds VXLAN encapsulation to the packet and forwards the packet with the VXLAN encapsulation to a VXLAN.

Abstract: An I/O board of a VXLAN switch receives a multicast data packet having a VXLAN encapsulation, removes the VXLAN encapsulation, determines that layer 3 multicast forwarding is to be performed for the multicast data packet, and sends the multicast data packet to a fabric board of the VXLAN switch. The fabric board determines that layer 3 multicast forwarding is to be performed by the fabric board for the multicast data packet. When a multicast group member port corresponding to the multicast data packet is a VLAN port, the fabric board sends the multicast data packet to each I/O board on the VXLAN switch. Each I/O board sends the received multicast data packet to a VLAN according to a layer 3 multicast group entry used for forwarding the received multicast data packet. The layer 3 multicast group entry being included in a local layer 3 multicast group table.

Abstract: The present disclosure provides a method for implementation of wireless relaying. The method is applied to a wireless relay device. The method comprises: a wireless relay device sends a probe request packet carrying a first detection code and device information of the wireless relay device; receive a probe response packet sent by a first wireless routing device, the probe response packet carrying an SSID and a password corresponding to the first wireless routing device; and send an authentication request packet to a second wireless routing device, the authentication request packet carrying the SSID and the password that is carried in the probe response packet sent by the second wireless routing device to the wireless relay device, and the second wireless routing device being one of the first wireless routing devices.

Abstract: Provided is a flow path detection method. The method comprises: a controller in an SDN network issuing reporting indication information to a forwarding device in the SDN network, wherein the reporting indication information is used for instructing the forwarding device to report, when receiving a message matching a pre-determined message feature, message forwarding information corresponding to the message, and the pre-determined message feature comprises: a source IP address and a destination IP address of a detection message for detecting a path, and a controller identifier of a controller; the controller receiving the message forwarding information reported by a plurality of forwarding devices according to the reporting indication information; and according to the received message forwarding information reported by the plurality of forwarding devices, determining a forwarding path between the source IP address and the destination IP address for the detection message.

Abstract: A method and device for forwarding a packet are disclosed. When a first access device connected with a database server is to be configured with a mirror image rule, an SDN controller can transmit a mirror image rule adding message carrying the mirror image rule to the first access device. Where, the mirror image rule comprises an IP address of the database server, a MAC address of a database audit device connected with a second access device and a VXLAN tunnel between the first access device and the second access device. When receiving a database access packet whose destination IP address is an IP address of the database server, the first access device may replace a destination MAC address of a mirror packet for the database access packet with a MAC address of the database audit device according to the mirror image rule and forward the encapsulated VXLAN packet.

Abstract: A receiving core reads a packet from an ingress interface, wherein the ingress interface is an interface corresponding to a forwarding group to which the receiving core belongs; the receiving core sends the read packet to a forwarding core in the forwarding group; and the forwarding core sends the packet to a corresponding egress interface.

Abstract: Disclosed is a method of loading a signature rule and a network device thereof. According to an example of the method, the network device may first receive a signature rule library sent by a cloud server, wherein the signature rule library contains one or more signature rules, each of which is associated with corresponding device type configuration information. The network device may determine for each signature rule whether device type configuration information associated with the signature rule matches local device type configuration information of the network device. If the device type configuration information associated with the signature rule matches the local device type configuration information of the network device, the network device may load the signature rule.