公开(公告)号：US11576114B2

公开(公告)日：2023-02-07

申请号：US16390800

申请日：2019-04-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yi Tu ,  Yulong Zeng ,  Xihua Huang

IPC: H04W88/06 ,  H04W48/18 ,  H04L45/24 ,  H04W8/04 ,  H04L47/193 ,  H04W72/04 ,  H04W28/08

Abstract: A data packet processing method, a terminal, and a gateway, where the terminal, determines to transmit network traffic using a first network and a second network simultaneously based on an aggregation flow table, and upon that determination, the terminal sends a quantity of first uplink data packets to the gateway using a first network interface card corresponding to the first network, and sends a quantity of second uplink data packets belonging to the same Transmission Control Protocol (TCP) connection as the first uplink data packets to the gateway using a second network interface card corresponding to the second network, where a source Internet Protocol (IP) address carried in each of the first uplink data packets is the IP address of the first network interface card, and a source IP address carried in each of the second uplink data packets is the IP address of the second network interface card.

公开(公告)号：US09571382B2

公开(公告)日：2017-02-14

申请号：US14616825

申请日：2015-02-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jianfei Li ,  Yulong Zeng

IPC: G01R31/08 ,  H04L12/705 ,  H04L12/18 ,  H04L12/801 ,  H04L12/823

CPC classification number: H04L45/18 ,  H04L12/1877 ,  H04L12/1886 ,  H04L47/12 ,  H04L47/32

Abstract: A method, a controller, and a system for processing a data packet are disclosed. The method includes receiving, by a controller, a data packet that is reported by a switch and does not match a forwarding rule; after it is determined that a type of the data packet is a broadcast data packet, generating a forwarding rule for the data packet, where the forwarding rule includes an action attribute being discarded; and sending the forwarding rule of the data packet to the switch, so that when receiving the data packet again, the switch discards the data packet according to the action attribute of the forwarding rule. In the present invention, a broadcast storm on a network can be avoided without shielding a port of a switch. Therefore, for a fully-connected network, a forwarding capability of a port and a quantity of available transmission links on the network are ensured.

Abstract translation: 公开了一种用于处理数据分组的方法，控制器和系统。 该方法包括由控制器接收由交换机报告并且不匹配转发规则的数据分组; 在确定数据分组的类型是广播数据分组之后，生成数据分组的转发规则，其中转发规则包括被丢弃的动作属性; 并将数据包的转发规则发送给交换机，使得当再次接收到数据包时，交换机根据转发规则的动作属性丢弃数据包。 在本发明中，可以避免网络上的广播风暴而不屏蔽交换机的端口。 因此，对于完全连接的网络，可以确保网络的端口转发能力和可用传输链路数量。

公开(公告)号：US09201691B2

公开(公告)日：2015-12-01

申请号：US14471198

申请日：2014-08-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Lin Gu ,  Zhiqiang Ma ,  Yulong Zeng

IPC: G06F13/00 ,  G06F9/48 ,  G06F9/52 ,  G06F3/06 ,  G06F9/50

CPC classification number: G06F9/4881 ,  G06F3/0604 ,  G06F3/065 ,  G06F3/067 ,  G06F9/5027 ,  G06F9/52 ,  G06F2003/0697

Abstract: A task coordination apparatus in a computing system having a distributed shared memory (DSM) coordinates the execution of two related tasks, wherein the second task has an execution variable which is modified by the first task. The task coordination apparatus creates a snapshot of a memory space in the distributed shared memory assigned to the first task and a cooperation watching area of the second task. The cooperation watching area contains a memory address pointing to a location where the execution variable of the second task is stored in the memory space assigned to the first task. The first task is allocated to a first computing node for execution, and the memory space assigned to it is updated according to the execution result. After updating the memory space, the second task is allocated to a second computing node for execution using the execution variable updated by the first task.

Abstract translation: 具有分布式共享存储器（DSM）的计算系统中的任务协调装置协调两个相关任务的执行，其中第二任务具有由第一任务修改的执行变量。 任务协调装置创建分配给第一任​​务的分布式共享存储器中的存储器空间的快照和第二任务的合作监视区域。 合作观看区域包含指向第二任务的执行变量被存储在分配给第一任​​务的存储器空间中的位置的存储器地址。 将第一任务分配给第一计算节点用于执行，并且根据执行结果更新分配给它的存储器空间。 在更新存储器空间之后，使用由第一任务更新的执行变量将第二任务分配给第二计算节点进行执行。