Abstract: Embodiments of the present disclosure provide a packet processing method and a network device, so as to effectively resolve a problem that a quantity of concurrent packet processing policies is limited in a network device due to scarce hardware resources of a packet forwarding chip. A method part in the embodiments of the present disclosure includes: obtaining, by a first network device, identification information; processing, by the first network device, a packet when receiving the packet, where a processed packet includes the identification information, and packets corresponding to different preset policy information include different identification information; and sending, by the first network device, the processed packet to a second network device, so that the second network device matches a corresponding policy for the processed packet based on the identification information.

Abstract: This application provides a method and an apparatus for determining a port orientation. The method includes: A first network device receives, through a first port, a protocol data unit PDU sent by a second network device. The first network device determines, based on the PDU, that the first port is an upstream port or a downstream port. In this embodiment of this application, the first network device may determine, based on the PDU sent by the second network device, whether the first port is the upstream port or the downstream port, to provide a basis for subsequently helping an SDN controller reduce load.

Abstract: Embodiments of this application disclose a communication method, and may be applied to a scenario such as switch networking (for example, high-performance computing HPC), the industrial Ethernet, or the like. The method includes: receiving first information sent by a second device, where the first information indicates a second MAC frame length supported by the second device; determining a third MAC frame length based on a first media access control MAC frame length and the second MAC frame length, where the first MAC frame length is a MAC frame length supported by the first device, and the first MAC frame length is the same as or different from the second MAC frame length; and communicating with the second device based on the third MAC frame length.

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: A method and an apparatus for determining hash algorithm information for load balancing, and a storage medium are provided, to determine, based on first hash algorithm information of a first communication device and information about a first quantity of first ports of the first communication device, second hash algorithm information that is used for load balancing and that is of a second communication device. In this application, a load balancing device receives a first message, where the first message includes the first hash algorithm information of the load balancing mode of the first communication device and the information about the first quantity of first ports of the first communication device. The load balancing device determines the second hash algorithm information of the load balancing mode of the second communication device based on the first hash algorithm information and the information about the first quantity.

Abstract: A network congestion processing method includes performing Explicit Congestion Notification (ECN) marking on a packet using first ECN configuration information, obtaining first network status information indicating a network status when the first ECN configuration information is used; determining second ECN configuration information based on the first ECN configuration information and the first network status information; and performing ECN marking on the packet using the second ECN configuration information.

Abstract: This application describes examples of a data processing method and apparatus. In one example, the method includes: If a target buffer that is corresponding to a target priority and that is on a network device reaches a first threshold, the network device sends a pause message to an upstream device, so that the upstream device stops sending a first data packet corresponding to the target priority. If a duration in which the network device stops buffering a second data packet is greater than a preset duration, and the target buffer falls back below a second threshold, the network device sends a sending resumption message to the upstream device, so that the upstream device sends a third data packet corresponding to the target priority.

Abstract: The present disclosure relates to priority flow control (PFC) storm detection and processing methods. In one example method, a first network node performs PFC detection on a first port queue of a first port, and determines that a first preset condition is met. The first preset condition includes: detection is performed in N consecutive first time segments, when the detection is performed in each first time segment, a quantity of first PFC frames sent by the first port queue to a second network node is greater than a first threshold, and a quantity of one or more data packets received by the first port queue from the second network node is less than a second threshold. The first PFC frame is used to indicate the second network node to suspend sending all data flows in the first port queue, and N is a positive integer.

Abstract: This application discloses network congestion control methods and apparatuses. In an implementation, a method comprises: obtaining, by the an intelligent network interface card comprised in a network congestion control apparatus, at least two types of traffic. Identifying, by the intelligent network interface card, algorithm matching features of the at least two types of traffic, and in response to determining to perform congestion control on one type of traffic of the at least two types of traffic, determining, by the intelligent network interface card, a congestion control algorithm that matches an algorithm matching feature of the one type of traffic. Performing, by the intelligent network interface card, congestion control on the one type of traffic according to the congestion control algorithm that matches the algorithm matching feature of the one type of traffic.

Abstract: A network congestion control method, a node and a system are disclosed, where the method is applied to a spine-leaf network system. The method includes: a spine node receives network information sent by the at least one leaf node, where the network information includes network topology information of the leaf node and a network performance indicator of the leaf node; networks the at least one leaf node and the spine node based on the network topology information of the at least one leaf node, to obtain a combined network topology; and if the combined network topology is a global network topology of the spine-leaf network system, performs network congestion control on the at least one leaf node based on the network performance indicator of the at least one leaf node.

Abstract: This application provides a collective communication method and a communication apparatus. The method includes: A first terminal device receives at least one second packet from a first network device, where the second packet includes information about a first process and information about a network device corresponding to the first process, the first process is used to execute a first task, and the information about the network device corresponding to the first process is information about a network device to which a terminal device including the first process belongs. The first terminal device determines a third packet based on the at least one second packet, where the third packet includes information about a target network device and information about all first processes that correspond to the target network device and that execute the first task.

Abstract: This application provides a port configuration method and a communications device. The method includes: obtaining, by a first communications device, an identifier of a second port group of a second communications device, where the identifier of the second port group is used to indicate configuration information of a first port of the first communications device, and establishing, by the first communications device, a connection to a second port in the second port group by using the first port, where the first port is any port of the first communications device, the second port is any port in the second port group, and the configuration information includes an internet protocol IP address; determining, by the first communications device, the configuration information of the first port based on the identifier of the second port group; and configuring, by the first communications device, the configuration information for the first port.

Abstract: A method implemented by a communication apparatus for processing a packet. The method includes obtaining, by the communication apparatus, a first packet, where the first packet includes a first-layer header. The first-layer header includes an identification field used to identify whether the first-layer header of the first packet includes information in a second-layer header. The communication apparatus then processes the first packet, which may include sending the first packet, forwarding the first packet, scheduling or marking the first packet, or the like.

Abstract: Example packet control methods and apparatus are described. One example method includes detecting, by a network node, a packet in a packet flow causing a congestion from an upstream node. The network node reduces a scheduling priority of the packet in the packet flow and generates a congestion isolation message, where the congestion isolation message includes description information of the packet flow. The congestion isolation message is sent to the upstream node to instruct the upstream node to reduce the scheduling priority of the packet in the packet flow.

Abstract: This application discloses a network congestion control method, apparatus, device, and system, and a storage medium. In an example method, a first switch receives a target signaling packet that is sent by a second switch in a case in which a network congestion status is a target network congestion status. The target signaling packet carries flow source information. The first switch sends, based on the target signaling packet, target flow control information to a network device corresponding to the flow source information. The target flow control information is used to indicate flow control.

Abstract: This application describes a congestion control method and apparatus. In this application, a network device obtains time information of one or more congestion packets in a sent first data stream, where the one or more congestion packet carries a flag indicating a congestion notification. When the first data stream is congested, the network device obtains a first congestion notification packet based on the time information of the one or more congestion packets in the first data stream, where the first congestion notification packet notifies that a packet is congested beyond a first specified interval. The network device then sends the first congestion notification packet. According to the solutions in this application, a rate of a data stream can be prevented from being increased when the data stream is congested, and packet transmission efficiency is improved.

Abstract: A network congestion control method, a node and a system are disclosed, where the method is applied to a spine-leaf network system. The method includes: a spine node receives network information sent by the at least one leaf node, where the network information includes network topology information of the leaf node and a network performance indicator of the leaf node; networks the at least one leaf node and the spine node based on the network topology information of the at least one leaf node, to obtain a combined network topology; and if the combined network topology is a global network topology of the spine-leaf network system, performs network congestion control on the at least one leaf node based on the network performance indicator of the at least one leaf node.

Abstract: A network congestion processing method includes performing Explicit Congestion Notification (ECN) marking on a packet using first ECN configuration information, obtaining first network status information indicating a network status when the first ECN configuration information is used; determining second ECN configuration information based on the first ECN configuration information and the first network status information; and performing ECN marking on the packet using the second ECN configuration information.

Abstract: This application provides a flow rate control method and apparatus. The flow rate control method in this application includes: receiving N explicit congestion notification packets CNPs from a first device, where the N CNPs correspond to a first data flow, and N is a natural number; and sending M CNPs to a second device based on the N CNPs, where the M CNPs correspond to the first data flow, and M is an integer greater than N. This application resolves a problem that rate increase processing is still performed on a data flow when the data flow is congested.

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.