Patent classifications
H04L45/74
Methods for active-active stateful network service cluster
For a managed network, some embodiments provide a method for a set of service nodes in an active-active service node cluster in conjunction with a host computer hosting a destination data compute node (DCN) to improve the efficiency of directing a data message to a service node storing state information for the flow to which the data message belongs. a first service node receives a data message in a particular data message flow for which it does not maintain state information. The first service node then identifies a second service node to process the data message and forwards the data message to the second service node. The second service node sends state information for the particular data message flow to the first service node, for the first service node to use to process subsequent data messages in the particular data message flow.
Methods for active-active stateful network service cluster
For a managed network, some embodiments provide a method for a set of service nodes in an active-active service node cluster in conjunction with a host computer hosting a destination data compute node (DCN) to improve the efficiency of directing a data message to a service node storing state information for the flow to which the data message belongs. a first service node receives a data message in a particular data message flow for which it does not maintain state information. The first service node then identifies a second service node to process the data message and forwards the data message to the second service node. The second service node sends state information for the particular data message flow to the first service node, for the first service node to use to process subsequent data messages in the particular data message flow.
Packet processing method, network node, and system
A packet processing method, a network node, and a system includes obtaining, by a first network node, a first packet that includes a segment list, where the segment list includes a segment identifier of a network node on a path used to forward the first packet, obtaining, by the first network node, a segment identifier of a second network node from the segment list, where the second network node is a next-hop segment node of the first network node on the path, replacing, by the first network node, a destination address of the first packet with the segment identifier of the second network node, and adding a network performance parameter of the first network node to the segment list to generate a second packet, and sending, by the first network node, the second packet to the second network node.
Packet processing method, network node, and system
A packet processing method, a network node, and a system includes obtaining, by a first network node, a first packet that includes a segment list, where the segment list includes a segment identifier of a network node on a path used to forward the first packet, obtaining, by the first network node, a segment identifier of a second network node from the segment list, where the second network node is a next-hop segment node of the first network node on the path, replacing, by the first network node, a destination address of the first packet with the segment identifier of the second network node, and adding a network performance parameter of the first network node to the segment list to generate a second packet, and sending, by the first network node, the second packet to the second network node.
Data transmission method, node and system
A data transmission method, a node, and a system, the method including receiving, by a forwarding node, a data packet, where a label stack of the data packet comprises a path identifier (path-ID), where the path-ID is an identifier of a constrained path, and where the constrained path is a path that consists of at least two nodes arranged in a specific order, determining, by the forwarding node, that the forwarding node is a node on the constrained path, selecting, by the forwarding node, a target label/target address from a local available label block/address block according to the path-ID and according to a preset rule, where the label block/address block comprises at least one label/address, searching for, by the forwarding node, a corresponding target interface according to the target label/target address, and forwarding, by the forwarding node, the data packet through the target interface.
Data transmission method, node and system
A data transmission method, a node, and a system, the method including receiving, by a forwarding node, a data packet, where a label stack of the data packet comprises a path identifier (path-ID), where the path-ID is an identifier of a constrained path, and where the constrained path is a path that consists of at least two nodes arranged in a specific order, determining, by the forwarding node, that the forwarding node is a node on the constrained path, selecting, by the forwarding node, a target label/target address from a local available label block/address block according to the path-ID and according to a preset rule, where the label block/address block comprises at least one label/address, searching for, by the forwarding node, a corresponding target interface according to the target label/target address, and forwarding, by the forwarding node, the data packet through the target interface.
Data processing method, apparatus, medium and device
The present specification discloses a data processing method, apparatus, medium and device. The method includes: receiving a QUIC data packet that is sent by a first device and that includes a CID; parsing the CID and determining a routing address based on a parsing result; and routing the received QUIC data packet to a second device based on the routing address, so the second device processes the QUIC data packet. When a data packet sent by a transmitting end device is received, a routing address of data transmission is determined by processing the received data packet, to quickly establish a data transmission channel between the transmitting end device and a receiving end device. As such, stored context information is not required, and connection errors caused by exceptions such as restarting and scaling in/out on a load balancer will not occur, thereby effectively improving processing efficiency of data transmission by using the QUIC protocol.
Data processing method, apparatus, medium and device
The present specification discloses a data processing method, apparatus, medium and device. The method includes: receiving a QUIC data packet that is sent by a first device and that includes a CID; parsing the CID and determining a routing address based on a parsing result; and routing the received QUIC data packet to a second device based on the routing address, so the second device processes the QUIC data packet. When a data packet sent by a transmitting end device is received, a routing address of data transmission is determined by processing the received data packet, to quickly establish a data transmission channel between the transmitting end device and a receiving end device. As such, stored context information is not required, and connection errors caused by exceptions such as restarting and scaling in/out on a load balancer will not occur, thereby effectively improving processing efficiency of data transmission by using the QUIC protocol.
Group based classification and policy enforcement for external network traffic
Techniques for group-based classification and policy enforcement at a network fabric edge for traffic that is being sent to external network destinations are disclosed herein. The techniques may include receiving, at a control plane of a network and from an edge node of the network, a request to provide mapping data associated with sending a packet to a destination. Based at least in part on an address prefix value associated with the destination, the control plane may determine that the destination is located in an external network. Additionally, a group identifier that is associated with the destination may be determined. In this way, an indication of the group identifier may be sent to the edge node such that the edge node may determine, based at least in part on the group identifier, a policy decision for routing the packet to the external network.
Group based classification and policy enforcement for external network traffic
Techniques for group-based classification and policy enforcement at a network fabric edge for traffic that is being sent to external network destinations are disclosed herein. The techniques may include receiving, at a control plane of a network and from an edge node of the network, a request to provide mapping data associated with sending a packet to a destination. Based at least in part on an address prefix value associated with the destination, the control plane may determine that the destination is located in an external network. Additionally, a group identifier that is associated with the destination may be determined. In this way, an indication of the group identifier may be sent to the edge node such that the edge node may determine, based at least in part on the group identifier, a policy decision for routing the packet to the external network.