Abstract: In a network congestion handling method, a first network device determines a target port, where the target port is an egress port that is in a pre-congestion state or a congestion state. The first network device sends a first notification to at least one second network device. The at least one second network device is capable of sending, through at least two forwarding paths, a data flow to a host corresponding to the target port. The first notification includes information of a network device to which the target port belongs and information of the target port. The first notification can enable the at least one second network device to perform an operation of avoiding network congestion. The network congestion handling method can effectively alleviate network congestion and improve network bandwidth utilization.

Abstract: In a method, a controller sends a first route update packet including a first route to a first forwarding device, so that the first forwarding device sends a third route update packet including a third route to at least one target forwarding device; a second forwarding device receives the third route update packet, determines a target link from the first forwarding device to the second forwarding device, and sends, based on a monitored state of the target link, a second route update packet including a second route and a target field to the controller; and the controller determines the state of the target link based on the target field in the second route update packet.

Abstract: A DCN includes N first-level subnetworks, each first-level subnetwork includes N second-level subnetworks, each kth-level subnetwork includes N (k+1)th-level subnetworks, each (K?1)th-level subnetwork includes multiple switches, and the DCN is a K-level network; each switch in the DCN has K subnetwork identifiers, the K subnetwork identifiers are respectively used to indicate each level of subnetwork to which the switch belongs and a number in a (K?1)th-level subnetwork to which the switch belongs; and the switch is separately interconnected with each switch in K direct connection switch groups, each direct connection switch group includes N?1 switches, and an ith-level subnetwork identifier of the N?1 switches included in an ith direct connection switch group of the K direct connection switch groups is different from an ith-level subnetwork identifier of the switch, and is the same as other K?1 subnetwork identifiers of the switch.

Abstract: A method and an apparatus are disclosed for generating an ACL table. A controller obtains a port type of each port of a first network device, and selects, based on the port type of each port, a target port whose port type is a preset type from all ports of the first network device. The controller generates a corresponding first-type access control list ACL entry for each target port, and generates one second-type ACL entry corresponding to a routing table of the first network device, where an action of the second-type ACL entry is redirecting to the routing table. The controller adds the second-type ACL entry and each first-type ACL entry to an ACL table of the first network device.

Abstract: A method for implementing load balancing, an apparatus, and a network system, where a controller obtains a port attribute of each port of a first switch in a mesh network, determines, according to the port attribute of each port of the first switch, a virtual routing and forwarding instance corresponding to each port of the first switch, where all user-side ports of the first switch correspond to a first virtual routing and forwarding instance, generates a forwarding table of the first switch according to a topology of the mesh network and the virtual routing and forwarding instance corresponding to each port of the first switch, where a first forwarding entry of the forwarding table includes the first virtual routing and forwarding instance, a destination network segment and at least two forwarding paths corresponding to the destination network segment, and sends the forwarding table to the first switch.

Abstract: A DCN includes N first-level subnetworks, each first-level subnetwork includes N second-level subnetworks, each kth-level subnetwork includes N (k+1)th-level subnetworks, each (K?1)th-level subnetwork includes multiple switches, and the DCN is a K-level network; each switch in the DCN has K subnetwork identifiers, the K subnetwork identifiers are respectively used to indicate each level of subnetwork to which the switch belongs and a number in a (K?1)th-level subnetwork to which the switch belongs; and the switch is separately interconnected with each switch in K direct connection switch groups, each direct connection switch group includes N?1 switches, and an ith-level subnetwork identifier of the N?1 switches included in an ith direct connection switch group of the K direct connection switch groups is different from an ith-level subnetwork identifier of the switch, and is the same as other K?1 subnetwork identifiers of the switch.

Abstract: In a method, a controller sends a first route update packet including a first route to a first forwarding device, so that the first forwarding device sends a third route update packet including a third route to at least one target forwarding device; a second forwarding device receives the third route update packet, determines a target link from the first forwarding device to the second forwarding device, and sends, based on a monitored state of the target link, a second route update packet including a second route and a target field to the controller; and the controller determines the state of the target link based on the target field in the second route update packet.

Abstract: A data center network system and a signal transmission system, where the signal transmission system includes one hub device, at least two switches, multiple colored optical modules, at least two multiplexers/demultiplexers, and at least two servers. The hub device, the at least two switches, the multiple colored optical modules, the at least two multiplexers/demultiplexers, and the at least two servers form a star network topology structure.

Abstract: The present disclosure discloses a method and an apparatus for generating an ACL table, and relates to the data center field. A controller obtains a port type of each port of a first network device, and selects, based on the port type of each port, a target port whose port type is a preset type from all ports of the first network device. The controller generates a corresponding first-type access control list ACL entry for each target port, and generates one second-type ACL entry corresponding to a routing table of the first network device, where an action of the second-type ACL entry is redirecting to the routing table. The controller adds the second-type ACL entry and each first-type ACL entry to an ACL table of the first network device.

Abstract: A method for implementing load balancing, an apparatus, and a network system, where a controller obtains a port attribute of each port of a first switch in a mesh network, determines, according to the port attribute of each port of the first switch, a virtual routing and forwarding instance corresponding to each port of the first switch, where all user-side ports of the first switch correspond to a first virtual routing and forwarding instance, generates a forwarding table of the first switch according to a topology of the mesh network and the virtual routing and forwarding instance corresponding to each port of the first switch, where a first forwarding entry of the forwarding table includes the first virtual routing and forwarding instance, a destination network segment and at least two forwarding paths corresponding to the destination network segment, and sends the forwarding table to the first switch.

Abstract: A data center network system and a signal transmission system, where the signal transmission system includes one hub device, at least two switches, multiple colored optical modules, at least two multiplexers/demultiplexers, and at least two servers. The hub device, the at least two switches, the multiple colored optical modules, the at least two multiplexers/demultiplexers, and the at least two servers form a star network topology structure.

Abstract: The present invention provides a data switching system, including K subsystems, where a first subsystem in the K subsystems includes M switching apparatuses, a first switching apparatus in the M switching apparatuses includes X network side ports, and the X network side ports include M?1 intra-group ports and K?1 inter-group ports, where the M?1 intra-group ports are respectively connected to M?1 switching apparatuses in the first subsystem except the first switching apparatus; and the K?1 inter-group ports are respectively connected to direct switching apparatuses, of the first switching apparatus, in K?1 subsystems in the K subsystems except the first subsystem. Such a structure improves a capacity of a switching system in a case in which no core switching apparatus is required.

Abstract: A data center network and a method for deploying the data center network. The data center network includes one core switch group, m cyclic arrayed waveguide grating (CAWG) groups, and m edge switch groups, where the core switch group includes k core switches; each CAWG group includes 2*Y N*N CAWGs, where the 2*Y CAWGs include Y uplink CAWGs and Y downlink CAWGs, the Y uplink CAWGs are connected to each core switch in the core switch group separately using an optical uplink, and the Y downlink CAWGs are connected to each core switch in the core switch group separately using an optical downlink; and each edge switch of an edge switch group is connected to an uplink CAWG and a downlink CAWG in a corresponding CAWG group separately. The present invention can reduce the number of optical fibers in a data center network.

Abstract: The present invention provides a data switching system, including K subsystems, where a first subsystem in the K subsystems includes M switching apparatuses, a first switching apparatus in the M switching apparatuses includes X network side ports, and the X network side ports include M-1 intra-group ports and K-1 inter-group ports, where the M-1 intra-group ports are respectively connected to M-1 switching apparatuses in the first subsystem except the first switching apparatus; and the K-1 inter-group ports are respectively connected to direct switching apparatuses, of the first switching apparatus, in K-1 subsystems in the K subsystems except the first subsystem. Such a structure improves a capacity of a switching system in a case in which no core switching apparatus is required.

Abstract: A data center network and a method for deploying the data center network. The data center network includes one core switch group, m cyclic arrayed waveguide grating (CAWG) groups, and m edge switch groups, where the core switch group includes k core switches; each CAWG group includes 2*Y N*N CAWGs, where the 2*Y CAWGs include Y uplink CAWGs and Y downlink CAWGs, the Y uplink CAWGs are connected to each core switch in the core switch group separately using an optical uplink, and the Y downlink CAWGs are connected to each core switch in the core switch group separately using an optical downlink; and each edge switch of an edge switch group is connected to an uplink CAWG and a downlink CAWG in a corresponding CAWG group separately. The present invention can reduce the number of optical fibers in a data center network.

Abstract: The present invention relates to network communications technologies, and discloses a method, an apparatus, and a network system for multi-port load sharing. The method includes: receiving packets destined for a destination; searching an address port mapping table for corresponding logical egress port information according to destination address information carried in the packets; searching a logical port table for information about a corresponding load sharing group according to the logical egress port information, where the load sharing group includes at least two physical ports and each physical port corresponds to at least two subchannels; and encapsulating the packets into at least one subchannel corresponding to each physical port in the load sharing group respectively according to a preset load sharing policy, and forwarding the packets to the destination through the corresponding physical port. The embodiments of the present invention are applicable to network communications.

Abstract: The present invention relates to network communications technologies, and discloses a method, an apparatus, and a network system for multi-port load sharing. The method includes: receiving packets destined for a destination; searching an address port mapping table for corresponding logical egress port information according to destination address information carried in the packets; searching a logical port table for information about a corresponding load sharing group according to the logical egress port information, where the load sharing group includes at least two physical ports and each physical port corresponds to at least two subchannels; and encapsulating the packets into at least one subchannel corresponding to each physical port in the load sharing group respectively according to a preset load sharing policy, and forwarding the packets to the destination through the corresponding physical port. The embodiments of the present invention are applicable to network communications.