Abstract:
Provided are a congestion control method, device and system. The congestion control method includes: receiving, by a source device, through a first port a local anti-congestion response message sent from a sink device, wherein the local anti-congestion response message is sent after the sink device determines that the length of data cached in a port sending queue for a second port of the sink device corresponding to the first port exceeds a threshold; and suspending, by the source device, sending of a data packet which needs to be sent to the second port through the first port. Hop-by-hop congestion control for the data packets of nodes in a content centric networking (CNN) is timely and accurately realized.
Abstract:
Embodiments of the present invention disclose a method for acquiring, by an SDN switch, an exact flow entry, applied to an SDN network, where the SDN network includes an SDN controller and multiple SDN switches, the SDN controller communicates with each SDN switch in an inband communication manner, and the method includes: first establishing, by a first SDN switch, a reliable connection to the SDN controller; then, sending a first control message based on a packet corresponding to a protocol for the reliable connection; adding path information of the first SDN switch to the control message; and subsequently, also adding, by each SDN switch that receives the first control message, path information of each SDN switch to the first control message, so that finally, the SDN controller knows an entire path, so as to deliver a flow table to the first SDN switch.
Abstract:
A method and an apparatus for compressing a content name are provided. In the method, a controller constructs a content name tree according to content names in a content database, where a first node of the content name tree stores a first-level prefix of a content name in the content database, and an Nth-level node of the content name tree stores prefixes of first N levels of the content name; and then the controller compresses a content name stored in the Mth-level node into a first content name stored in a father node of the Mth-level node when determining that the content name stored in each Mth-level node in the content name tree is corresponding to a first network node in a network. Thus, compression of a content name in a content name database is achieved, and space occupied by the content name is saved.
Abstract:
Embodiments of the present invention disclose a method for acquiring, by an SDN switch, an exact flow entry, applied to an SDN network, where the SDN network includes an SDN controller and multiple SDN switches, the SDN controller communicates with each SDN switch in an inband communication manner, and the method includes: first establishing, by a first SDN switch, a reliable connection to the SDN controller; then, sending a first control message based on a packet corresponding to a protocol for the reliable connection; adding path information of the first SDN switch to the control message; and subsequently, also adding, by each SDN switch that receives the first control message, path information of each SDN switch to the first control message, so that finally, the SDN controller knows an entire path, so as to deliver a flow table to the first SDN switch.
Abstract:
A short-range wireless communication method includes a sending device configured to broadcast a data packet; the sending device performs, at a predetermined time point within a time periodicity associated with the broadcasting of the data packet and in a predetermined frequency range, detection on response information fed back by at least one receiving device based on reception of the data packet, where the response information indicates at least a message that the data packet is not successfully received by any one of the at least one receiving device; and the sending device retransmits the data packet if the response information is obtained through detection.
Abstract:
A method and associated apparatus provide for a management node to send to a terminal node, a negotiation request used to update a receiving/sending switching interval to first switching time. The receiving/sending switching interval includes a first receiving/sending switching interval of the management node and a second receiving/sending switching interval of the terminal node. The terminal node receives the negotiation request, feeds back acknowledgment response information to the management node in response to the negotiation request, and updates the second receiving/sending switching interval to the first switching time. The management node receives the acknowledgment response information. The management node updates the first receiving/sending switching interval to the first switching time based on the acknowledgment response information.
Abstract:
Embodiments of the present invention provide a method for routing and forwarding. The method includes: receiving, by a network controller, a routing request message sent by a requesting routing node, where the routing request message carries a content name of requested content; determining, by the network controller according to a network topology diagram and registration information of the requested content, a proper forwarding path; and delivering, by the network controller, routing information to each routing node on the forwarding path. In the embodiments of the present invention, a network controller is introduced, and registration information and a network topology diagram are stored in the network controller, so that the network controller may be used to determine a forwarding path of a content request packet, which reduces blindness of routing and forwarding of the content request packet in an ICN network and improves efficiency of routing and forwarding.
Abstract:
The method includes the following steps. First, a controller receives a data packet that is reported by a switch connected to a source host; then the controller searches a local media access control (MAC) address table of physical addresses of devices to determine whether a destination address of the data packet exists, and the controller acquires a destination port if no destination address of the data packet exists, where the destination port is a port of a switch connected to a destination host, and the destination host is another host different from the source host; and finally, the controller uses the destination port as a destination address to generate a routing table, and sends the routing table to the switch connected to the source host, so that the switch connected to the source host forwards the data packet according to the routing table.