CN113055293A

CN113055293A - Routing method and device in software defined wide area network and communication system

Info

Publication number: CN113055293A
Application number: CN201911380368.4A
Authority: CN
Inventors: 黄一宏; 吴波; 曹倩
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2019-12-27
Filing date: 2019-12-27
Publication date: 2021-06-29
Anticipated expiration: 2039-12-27
Also published as: CN113055293B

Abstract

Disclosed are a routing method and device, a communication system and a computer storage medium in a software defined wide area network, which belong to the technical field of communication. The first device receives a first data message sent by the second device through the first tunnel, wherein the first device is an exit device of the first tunnel, and the second device is an entrance device of the first tunnel. The first device determines first path constraint information corresponding to the first service according to the first data message, wherein the first path constraint information is used for determining a first path constraint condition which is satisfied by a first path for transmitting the first service. The first device determines that the first device does not satisfy a first path constraint condition, and sends a first feedback message to the second device, wherein the first feedback message carries first indication information, and the first indication information is used for indicating to the second device that the first device cannot be used as a node for transmitting a first service on a first path. The method and the device improve the instantaneity of the network equipment for acquiring the message transmission path.

Description

Routing method and device in software defined wide area network and communication system

Technical Field

The present application relates to the field of communications technologies, and in particular, to a routing method and apparatus in a software defined wide area network, and a communication system.

Background

Communication networks are currently generally managed by network control devices, which can determine the path of transmission of messages in the communication network. The network control device is connected to each network device in the communication network. Each network device respectively acquires the state information of the tunnel where the output port of the network device is located, and sends the state information of the tunnel to the network control device. And the network control equipment determines a message transmission path in the communication network according to the network topology information and the received state information of the tunnel. And then the network control equipment sends the determined message transmission path to each network equipment, so that each network equipment transmits the message by adopting the message transmission path determined by the network control equipment. The state information of the tunnel includes information such as tunnel bandwidth and transmission delay of the tunnel.

However, the network control device determines a message transmission path in the communication network, the network device needs to send status information of a tunnel to the network control device, the network control device needs to send the determined message transmission path to each network device, and an interaction process between the network control device and each network device is complex, so that the network device consumes a long time in the whole process from the acquisition of the status information of the tunnel to the acquisition of the message transmission path, and the network device has poor instantaneity in acquiring the message transmission path.

Disclosure of Invention

The application provides a routing method and device in a software-defined wide area network, a communication system and a computer storage medium, which can solve the problem of poor instantaneity of a network device for acquiring a message transmission path.

In a first aspect, a routing method in an SD-WAN is provided, which includes: the first device receives a first data message sent by the second device through the first tunnel, wherein the first device is an exit device of the first tunnel, and the second device is an entrance device of the first tunnel. The first device determines first path constraint information corresponding to the first service according to the first data message, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service. The first device determines that the first device does not satisfy a first path constraint condition, and sends a first feedback message to the second device, wherein the first feedback message carries first indication information, and the first indication information is used for indicating to the second device that the first device cannot be used as a node for transmitting a first service on a first path.

In the application, the first device determines, according to the received first data packet, first path constraint information corresponding to a first service, and then when determining, according to the first path constraint information, that the first device does not satisfy a first path condition, the first device can send a first feedback packet to the second device, so as to indicate, to the second device, that the first device cannot serve as a node on the first path for transmitting the first service. The first path can be selected through interaction between the first device and the second device, the first device and the second device do not need to interact with the control device, and dynamic routing is achieved on a data plane, so that routing efficiency is improved. Meanwhile, the data transmission quantity between the first equipment and the control equipment and between the second equipment and the control equipment is reduced, and the network overhead is reduced.

The first device determines that the first device does not satisfy the first path constraint condition corresponding to the first path constraint information, that is, the first device determines that the first device cannot serve as a node for transmitting the first service on the first path.

Optionally, the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate.

In the first case, the first device is an intermediate device in the SD-WAN for transmitting a service packet of the first service:

when the first path constraint information includes bandwidth, delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the first path constraint condition includes: a target tunnel meeting the bandwidth included in the first path constraint information exists in the tunnel taking the first device as the entrance device, and the route of the target tunnel can reach the exit device used for transmitting the service message of the first service in the SD-WAN; the actual transmission delay, the actual jitter, the actual packet loss rate, the actual error rate and the actual bandwidth occupancy rate of the first data message on the first tunnel respectively meet the delay, the jitter, the packet loss rate, the error rate and the bandwidth occupancy rate included in the first path constraint information. When a target tunnel meeting the bandwidth included by the first path constraint information does not exist in a tunnel using the first device as an entry device, the actual transmission delay of the first data packet in the first tunnel is greater than the delay included by the first path constraint information, the actual jitter in the first tunnel exceeds the jitter range included by the first path constraint information, the actual packet loss rate in the first tunnel is higher than the packet loss rate included by the first path constraint information, the actual error rate in the first tunnel is greater than the error rate included by the first path constraint information, and/or the actual bandwidth occupancy of other services in the first tunnel is greater than the bandwidth occupancy included by the first path constraint information, the first device determines that the first device does not meet the path constraint condition corresponding to the first path constraint information.

In the second case, the first device is an egress device in the SD-WAN for transmitting a service packet of the first service:

when the first path constraint information includes time delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the first path constraint condition corresponding to the first path constraint information includes: the actual transmission delay, the actual jitter, the actual packet loss rate, the actual error rate and the actual bandwidth occupancy rate of the first data message on the first tunnel respectively meet the delay, the jitter, the packet loss rate, the error rate and the bandwidth occupancy rate included in the first path constraint information. When the actual transmission delay of the first data message in the first tunnel is greater than the delay included in the first path constraint information, the actual jitter in the first tunnel exceeds the jitter range included in the first path constraint information, the actual packet loss rate in the first tunnel is higher than the packet loss rate included in the first path constraint information, the actual error rate in the first tunnel is greater than the error rate included in the first path constraint information, and/or the actual bandwidth occupancy of other services in the first tunnel is greater than the bandwidth occupancy included in the first path constraint information, the first device determines that the first device does not satisfy the first path constraint condition corresponding to the first path constraint information.

When the first path constraint information includes only the bandwidth, the first device may default itself to satisfy the first path constraint condition. When the first device receives the first data message, it is determined that the routing of the first service is completed, and a first path for transmitting the first service in the SD-WAN is obtained.

Optionally, the method may further include: and the first equipment receives a second data message sent by the third equipment through the second tunnel, wherein the first equipment is the exit equipment of the second tunnel, and the third equipment is the entrance equipment of the second tunnel. And the first equipment determines second path constraint information corresponding to the second service according to the second data message, wherein the second path constraint information is used for determining a second path constraint condition met by a second path for transmitting the second service. And the first equipment determines that the first equipment meets the second path constraint condition, and forwards the updated second data message to fourth equipment through a third tunnel, wherein the first equipment is the inlet equipment of the third tunnel, and the fourth equipment is the outlet equipment of the third tunnel.

The first device determines that the first device itself meets the second path constraint condition corresponding to the second path constraint information, that is, the first device determines that the first device itself can serve as a node on the second path for transmitting the second service.

In the method, the first device determines second path constraint information corresponding to a second service according to the received second data message, and then the first device can send the updated second data message to the fourth device when determining that the first device meets a second path condition according to the second path constraint information, and the first device can realize selection of the second path without interaction with the control device, so that the routing efficiency is improved. Meanwhile, the data transmission quantity between the first equipment and the control equipment is reduced, and the network overhead is reduced.

In the first case, the first device is an intermediate device in the SD-WAN for transmitting a service packet of the second service:

when the second path constraint information includes bandwidth, delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the second path constraint condition includes: a target tunnel meeting the bandwidth included by the second path constraint information exists in the tunnel taking the first device as the entrance device, and the route of the target tunnel can reach the exit device used for transmitting the service message of the second service in the SD-WAN; and the actual transmission delay, the actual jitter, the actual packet loss rate, the actual error rate and the actual bandwidth occupancy rate of the second data message on the second tunnel respectively meet the delay, the jitter, the packet loss rate, the error rate and the bandwidth occupancy rate included in the second path constraint information. When a target tunnel meeting the bandwidth included by the second path constraint information exists in a tunnel taking the first device as the entrance device, the actual transmission delay of the second data packet on the second tunnel is smaller than the delay included by the second path constraint information, the actual jitter on the second tunnel is within the jitter range included by the second path constraint information, the actual packet loss rate on the second tunnel is not higher than the packet loss rate included by the second path constraint information, the actual bit error rate on the second tunnel is smaller than or equal to the bit error rate included by the second path constraint information, and the actual bandwidth occupancy rate of other services on the second tunnel is smaller than or equal to the bandwidth occupancy rate included by the second path constraint information, the first device determines that the first device meets the second path constraint condition.

In the second case, the first device is an egress device in the SD-WAN for transmitting a service packet of the second service:

when the second path constraint information includes delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the second path constraint condition includes: and the actual transmission delay, the actual jitter, the actual packet loss rate, the actual error rate and the actual bandwidth occupancy rate of the second data message on the second tunnel respectively meet the delay, the jitter, the packet loss rate, the error rate and the bandwidth occupancy rate included in the second path constraint information. When the actual transmission delay of the second data packet in the second tunnel is less than or equal to the delay included in the second path constraint information, the actual jitter in the second tunnel is within the jitter range included in the second path constraint information, the actual packet loss rate in the second tunnel is not higher than the packet loss rate included in the second path constraint information, the actual bit error rate in the second tunnel is less than or equal to the bit error rate included in the second path constraint information, and the actual bandwidth occupancy of other services in the second tunnel is less than or equal to the bandwidth occupancy included in the second path constraint information, the first device determines that the first device satisfies the second path constraint condition.

When the second path constraint information only includes the bandwidth, the first device may default that the first device satisfies the second path constraint condition, and when the first device receives the second data packet, it determines to complete the routing of the second service, so as to obtain a second path for transmitting the second service in the SD-WAN.

Optionally, the method further comprises: and the first device receives a second feedback message sent by the fourth device, wherein the second feedback message carries second indication information, and the second indication information is used for indicating to the first device that the fourth device cannot be used as a node for transmitting the second service on the second path. And the first equipment determines that the fourth equipment does not meet the second path constraint condition according to the second indication information.

Illustratively, when the third tunnel is a bidirectional tunnel, the fourth device sends the second feedback packet to the first device through the third tunnel. Or, the fourth device may send the second feedback packet to the first device in a point-to-point transmission manner.

In one implementation, after the first device determines, according to the second indication information, that the fourth device does not satisfy the second path constraint condition, the method further includes: the first device reselects a downstream device on the second path. Optionally, the first device reselects a downstream device on the second path, including: and the first equipment sends the updated second data message to the fifth equipment through the fourth tunnel, wherein the first equipment is the inlet equipment of the fourth tunnel, and the fifth equipment is the outlet equipment of the fourth tunnel.

In the application, the first device can reselect the downstream device on the second path according to the received second indication information, and the first device can realize the reselection of the second path through the interaction with the fourth device, thereby realizing dynamic routing. Meanwhile, the data transmission quantity between the first equipment and the control equipment is reduced, and the network overhead is reduced.

In another implementation, after the first device determines, according to the second indication information, that the fourth device does not satisfy the second path constraint condition, the method further includes: and the first equipment sends a third feedback message to the third equipment, wherein the third feedback message carries third indication information, and the third indication information is used for indicating the third equipment that the first equipment cannot be used as a node for transmitting the second service on the second path.

In the application, when the first device does not select the downstream node which can be used as the second path on the second path for transmitting the second service, the first device sends the third feedback message to the third device to indicate to the third device that the first device cannot be used as the node on the second path for transmitting the second service, so that the first device can select the second path by interacting with the third device, and the first device and the third device do not need to interact with the control device, thereby improving the routing efficiency. Meanwhile, the data transmission quantity between the first equipment and the control equipment is reduced, and the network overhead is reduced.

Optionally, the first data packet is a probe packet, and the probe packet carries the first path constraint information.

Optionally, the receiving, by the first device, the first data packet sent by the second device through the first tunnel includes: and the first equipment receives the detection message sent by the second equipment through the first tunnel according to a preset time interval.

In the application, in the service transmission process, the first device can detect whether the first device meets the service requirement or not at intervals according to the received detection message, so that the reliability of service transmission is ensured.

Optionally, the first data packet is a service packet, and the service packet carries the first path constraint information.

Optionally, the determining, by the first device, the first path constraint information corresponding to the first service according to the first data packet includes: and the first equipment determines locally stored first path constraint information corresponding to the service type according to the service type of the first data message.

Because the first path constraint information is stored locally, the first device does not need to add the first path constraint information in the received service message, that is, the first device does not need to change the service message, thereby improving the message transmission efficiency and further improving the routing efficiency.

Optionally, a header of the first data packet includes a first field and a second field, where the first field is used to carry the first path constraint information, and the second field is used to indicate whether the first path constraint information carried by the first field is valid.

In a second aspect, a routing method in an SD-WAN is provided. The method comprises the following steps: the second device sends the first data message to the first device through the first tunnel, the second device is an entrance device of the first tunnel, and the first device is an exit device of the first tunnel. The second equipment receives a first feedback message sent by the first equipment, wherein the first feedback message carries first indication information. And the second equipment determines that the first equipment can not be used as a node for transmitting the first service on the first path according to the first indication information. And the second device sends a second data message to a third device through a second tunnel, wherein the second device is an entrance device of the second tunnel, and the third device is an exit device of the second tunnel.

In the application, after the second device sends the first data message to the first device, when the second device receives the first feedback message sent by the first device, it is determined that the first device cannot serve as a node for transmitting the first service on the first path according to first indication information carried in the first feedback message, the first path can be selected by interaction between the first device and the second device, and the first device and the second device do not need to interact with the control device, so that dynamic routing of a data plane is realized, and routing efficiency is improved. Meanwhile, the data transmission quantity between the first equipment and the control equipment and between the second equipment and the control equipment is reduced, and the network overhead is reduced.

Optionally, after the second device sends the second data packet to the third device through the second tunnel, the method further includes: and the second equipment receives a second feedback message sent by the third equipment, wherein the second feedback message carries second indication information. And the second equipment determines that the third equipment can not be used as a node for transmitting the first service on the first path according to the second indication information.

In the application, the second device can reselect the downstream device on the first path according to the received second indication information, and the second device can reselect the second path through interaction with the third device, so that dynamic routing is realized. Meanwhile, the data transmission quantity between the second equipment and the control equipment is reduced, and the network overhead is reduced.

Optionally, the second device sends a notification message to the control device, where the notification message carries third indication information, and the third indication information is used to indicate to the control device that the first path does not exist in the SD-WAN.

Optionally, the notification message is a BGP message. For example, when the notification packet is a BGP open (open) message, the third indication information may be carried in an optional parameters (optional parameters) field of the BGP open message. The third indication information carries a service type of the first service, and the service type of the first service may be encoded by a type-length-value (TLV) and then carried in an optional parameter field of the BGP open message.

Optionally, the first data packet and the second data packet are detection packets, and the detection packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

Illustratively, the second device generates a detection packet including the first path constraint information after determining that the second device itself satisfies the first path constraint condition corresponding to the first path constraint information. The detection message is used for detecting a first path of the first service in the SD-WAN, and the detection message does not usually carry specific service information.

Optionally, after the second device sends the second data packet to the third device through the second tunnel, the method further includes: and the second equipment sends the detection message to the third equipment through the second tunnel according to a preset time interval.

In the application, the second device can send the detection message to the third device according to the predetermined time interval in the service transmission process, and the third device can detect whether the third device meets the service requirement or not at intervals according to the received detection message, so that the reliability of service transmission is ensured.

Optionally, the first data packet and the second data packet are service packets, the service packets carry first path constraint information, and the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

For example, in the process of transmitting the first service packet, after receiving the service packet sent by the sending end device, the second device may insert the first path constraint information into the service packet to obtain the data packet.

Optionally, the method further comprises: and the second equipment receives the routing instruction which is sent by the control equipment and aims at the first service. And the second equipment acquires first path constraint information according to the routing instruction, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service.

Illustratively, when the control device determines that one or more tunnels in the current transmission path of the first service do not meet the service requirement of the first service, the control device may send a routing instruction to the second device.

Optionally, the routing instruction includes a service type of the first service, and the second device obtains the first path constraint information according to the routing instruction, including: and the second equipment determines locally-stored first path constraint information corresponding to the service type according to the service type of the first service.

The first path constraint information is stored locally, so that the control device only needs to carry the service type of the first service without adding the first path constraint information in the routing instruction, and transmission resources can be saved.

Optionally, the routing instruction includes first path constraint information.

Optionally, the method further comprises: and the second equipment receives the service message of the first service sent by the sending end equipment. The second device determines locally stored first path constraint information corresponding to the service type according to the service type of the service packet of the first service, wherein the first path constraint information is used for determining a first path constraint condition which is satisfied by a first path for transmitting the first service.

Optionally, the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate or bandwidth occupancy.

In a third aspect, a first device in an SD-WAN is provided. Comprises a plurality of functional modules, which interact with each other to implement the routing method in the SD-WAN as described in the first aspect or any one of the possible implementation manners of the first aspect. The plurality of functional modules comprise a transceiver module and a processing module.

And the transceiver module is configured to receive a first data packet sent by a second device through a first tunnel, where the first device is an exit device of the first tunnel, and the second device is an entry device of the first tunnel.

And the processing module is used for determining first path constraint information corresponding to the first service according to the first data message, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service.

And the transceiver module is further configured to determine that the transceiver module does not satisfy the first path constraint condition, and send a first feedback packet to the second device, where the first feedback packet carries first indication information, and the first indication information is used to indicate, to the second device, that the first device cannot serve as a node on the first path for transmitting the first service.

Optionally, the transceiver module is further configured to receive, through the second tunnel, a second data packet sent by a third device, where the first device is an egress device of the second tunnel, and the third device is an ingress device of the second tunnel.

And the processing module is further configured to determine second path constraint information corresponding to the second service according to the second data packet, where the second path constraint information is used to determine a second path constraint condition that is satisfied by a second path for transmitting the second service.

And the transceiver module is further configured to determine that the transceiver module satisfies the second path constraint condition, and forward the updated second data packet to a fourth device through a third tunnel, where the first device is an ingress device of the third tunnel, and the fourth device is an egress device of the third tunnel.

Optionally, the transceiver module is further configured to receive a second feedback packet sent by the fourth device, where the second feedback packet carries second indication information, and the second indication information is used to indicate, to the first device, that the fourth device cannot serve as a node for transmitting the second service on the second path.

And the processing module is further used for determining that the fourth equipment does not meet the second path constraint condition according to the second indication information.

Optionally, the processing module is further configured to reselect a downstream device on the second path.

Optionally, the processing module is further configured to: and sending the updated second data message to a fifth device through a fourth tunnel, wherein the first device is an inlet device of the fourth tunnel, and the fifth device is an outlet device of the fourth tunnel.

Optionally, the transceiver module is further configured to send a third feedback packet to the third device, where the third feedback packet carries third indication information, and the third indication information is used to indicate, to the third device, that the first device cannot serve as a node on the second path for transmitting the second service.

Optionally, the first data packet is a detection packet, and the detection packet carries the first path constraint information.

Optionally, the transceiver module is further configured to: and receiving the detection message sent by the second equipment through the first tunnel according to a preset time interval.

Optionally, the processing module is configured to: and determining locally stored first path constraint information corresponding to the service type according to the service type of the first data message.

In a fourth aspect, a second device in an SD-WAN is provided. Comprises a plurality of functional modules which interact to implement the routing method in the SD-WAN as described in the second aspect or any of the possible implementations of the second aspect. The plurality of functional modules comprise a transceiver module and a processing module. And the transceiver module is used for sending the first data message to the first device through the first tunnel, the second device is an entrance device of the first tunnel, and the first device is an exit device of the first tunnel.

The transceiver module is further configured to receive a first feedback message sent by the first device, where the first feedback message carries the first indication information.

And the processing module is used for determining that the first equipment cannot be used as a node for transmitting the first service on the first path according to the first indication information.

The transceiver module is further configured to send a second data packet to a third device through a second tunnel, where the second device is an ingress device of the second tunnel, and the third device is an egress device of the second tunnel.

Optionally, the transceiver module is further configured to receive a second feedback message sent by the third device, where the second feedback message carries the second indication information.

And the processing module is further configured to determine, according to the second indication information, that the third device cannot serve as a node on the first path for transmitting the first service.

Optionally, the transceiver module is further configured to send a notification message to the control device, where the notification message carries third indication information, and the third indication information is used to indicate to the control device that the first path does not exist in the SD-WAN.

Optionally, the transceiver module is further configured to send, by the second device, the probe packet to the third device through the second tunnel according to the predetermined time interval.

Optionally, the transceiver module is further configured to receive a routing instruction for the first service sent by the control device.

The processing module is further configured to obtain first path constraint information according to the routing instruction, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

Optionally, the routing instruction includes a service type of the first service, and the processing module is further configured to: and determining locally stored first path constraint information corresponding to the service type according to the service type of the first service.

Optionally, the routing instruction includes first path constraint information.

Optionally, the transceiver module is further configured to receive a service packet of the first service sent by the sending end device. The processing module is further configured to determine, according to the service type of the service packet of the first service, locally stored first path constraint information corresponding to the service type, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

In a fifth aspect, there is provided a first device in an SD-WAN, comprising: a processor and a memory;

the memory for storing a computer program, the computer program comprising program instructions;

the processor is configured to invoke the computer program to implement the routing method in the SD-WAN as described in the first aspect or any possible implementation manner of the first aspect.

In a sixth aspect, there is provided a second device in an SD-WAN, comprising: a processor and a memory;

the processor is configured to invoke the computer program to implement the routing method in the SD-WAN as described in the second aspect or any possible implementation manner of the second aspect.

In a seventh aspect, a first device in an SD-WAN is provided, including: the device comprises a communication interface and a processor connected with the communication interface. The method according to the first aspect or any one of the possible implementation manners of the first aspect is implemented according to the communication interface and the processor.

In an eighth aspect, there is provided a second device in an SD-WAN, comprising: the device comprises a communication interface and a processor connected with the communication interface. The method according to the second aspect or any possible implementation form of the second aspect is implemented according to the communication interface and the processor.

A ninth aspect provides a communication system in an SD-WAN, comprising a first device as described in any one of the third, fifth or seventh aspects, and a second device as described in any one of the fourth, sixth or eighth aspects. Alternatively, the first device may be an intermediate device or an exit device on the path and the second device may be an entrance device or an intermediate device.

A tenth aspect provides a computer storage medium having stored thereon instructions that, when executed by a processor, implement a method as described in the first aspect or any possible implementation manner of the first aspect; or implementing a method as described in the second aspect or any possible implementation manner of the second aspect.

The beneficial effect that technical scheme that this application provided brought includes at least:

according to the SD-WAN routing method, the network control equipment is not required to select the message transmission path, and each network equipment in the SD-WAN can dynamically select the transmission path in the message transmission process, so that the SD-WAN routing method is suitable for message transmission of SD-WAN with a large number of network equipment and cross-domain transmission services. In addition, in the message transmission process, the network equipment does not need to interact with the control equipment of the SD-WAN, so that the real-time property of message transmission is ensured. Meanwhile, the data transmission quantity between the inlet equipment and the control equipment on the transmission path in the SD-WAN is reduced, and the network overhead is reduced.

Drawings

Fig. 1 is a schematic structural diagram of a communication system in an SD-WAN according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of another SD-WAN communication system provided in an embodiment of the present application;

fig. 3 is a schematic flowchart of a routing method in an SD-WAN according to an embodiment of the present application;

fig. 4 is a flowchart of a method for obtaining path constraint information according to an embodiment of the present application;

fig. 5 is a flowchart of another method for obtaining path constraint information according to an embodiment of the present application;

FIG. 6 is a schematic flow chart diagram illustrating another SD-WAN routing method according to an embodiment of the present application;

FIG. 7 is a schematic flow chart diagram illustrating another alternative SD-WAN routing method according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a service packet using an IOAM mechanism according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a VXLAN packet adopting an IOAM mechanism according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a probe packet according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of another probe packet provided in the embodiment of the present application;

fig. 12 is a schematic structural diagram of a feedback packet according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of another feedback packet provided in the embodiment of the present application;

FIG. 14 is a schematic flow chart diagram illustrating another alternative routing method in the SD-WAN according to the embodiment of the present application;

fig. 15 is a schematic flowchart of a routing method in an SD-WAN according to an embodiment of the present application;

fig. 16 is a schematic structural diagram of a routing device in an SD-WAN according to an embodiment of the present application;

FIG. 17 is a schematic diagram of another SD-WAN routing device according to an embodiment of the present application;

FIG. 18 is a block diagram of a routing device in an SD-WAN according to an embodiment of the present application;

fig. 19 is a block diagram of another alternative routing device in an SD-WAN according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

A software defined wide area network (SD-WAN) includes one or more tunnels. The tunnel in the embodiment of the present application refers to a logical connection established by a network tunneling protocol. The SD-WAN may be a point of presence (POP) overlay network, and accordingly, the tunnel in the SD-WAN is an overlay tunnel. In a specific embodiment, the overlay tunnel may be established by using a network tunnel protocol such as a General Routing Encapsulation (GRE) protocol, a virtual extensible local area network (VXLAN) protocol, or an internet protocol security (IPsec) protocol.

The SD-WAN supports different transmission paths for messages of different types of services. For example, the SD-WAN supports transmission of an important packet through a transmission path based on a Multi Protocol Label Switching (MPLS) technology, and transmission of an unimportant packet through a transmission path based on a broadband network or a Long Term Evolution (LTE) technology, which can improve a transmission resource utilization rate and an operation cost (OPEX). The transmission path refers to a logical path between an ingress device and an egress device in the SD-WAN for transmitting a traffic packet, and the transmission path includes one or more tunnels.

Fig. 1 is a schematic structural diagram of a communication system in an SD-WAN according to an embodiment of the present application. As shown in fig. 1, the communication system in the SD-WAN includes a plurality of network devices 101A to 101F (collectively referred to as network devices 101) in the SD-WAN. The number of network devices in fig. 1 is for illustrative purposes only and is not meant to be a limitation of the SD-WAN as referred to in the embodiments of the present application.

Referring to fig. 1, a solid line between two network devices 101 represents a tunnel established between the two network devices 101. For example, a tunnel is established between network device 101A and network device 101B, between network device 101C and network device 101D, respectively; a tunnel is respectively established between the network device 101C and the network device 101A, the network device 101B, the network device 101D, the network device 101E and the network device 101F; and so on.

In a specific embodiment, the network devices transmit the messages through a tunnel. In the embodiment of the present application, in two network devices with a tunnel, a network device that receives a packet first is referred to as an ingress device of the tunnel, and a network device that receives a packet later is referred to as an egress device of the tunnel. The network device connected with the sending end device in the SD-WAN is called an inlet device used for transmitting the service message in the SD-WAN, the network device connected with the receiving end device in the SD-WAN is called an outlet device used for transmitting the service message in the SD-WAN, and the network device positioned between the inlet device used for transmitting the service message and the outlet device used for transmitting the service message in the SD-WAN is called an intermediate device used for transmitting the service message in the SD-WAN. In one embodiment, the network device 101 may be a physical device or a virtual device. The ingress and egress devices of the transmission path in the SD-WAN may be Customer Premises Equipment (CPE), a router, a switch, or the like, and the intermediate device of the transmission path in the SD-WAN may be a router, a switch, or the like.

The transmission path in the SD-WAN includes two or more network devices thereon, and accordingly, the transmission path in the SD-WAN includes one or more tunnels. When a transmission path in the SD-WAN includes only two network devices, i.e., only an ingress device for transmitting a traffic packet and an egress device for transmitting a traffic packet, the transmission path includes one tunnel. When a transmission path in the SD-WAN includes more than two network devices, that is, an ingress device for transmitting a service packet, an intermediate device for transmitting a service packet, and an egress device for transmitting a service packet, the transmission path includes a plurality of tunnels.

Illustratively, in the SD-WAN shown in fig. 1, the network device 101A is an ingress device in the SD-WAN for transmitting the service packet, the network device 101F is an egress device in the SD-WAN for transmitting the service packet, and the network devices 101B to 101E are all intermediate devices in the SD-WAN for transmitting the service packet. There are multiple transmission paths between network device 101A and network device 101F, including, for example, the following 4 transmission paths, transmission path 1: network device 101A-network device 101C-network device 101F; transmission path 2: network device 101A-network device 101D-network device 101F; transmission path 3: network device 101A-network device 101C-network device 101E-network device 101F; transmission path 4: network device 101A-network device 101D-network device 101E-network device 101F. Referring to fig. 1, a tunnel L1 is established between network device 101A and network device 101C, a tunnel L2 is established between network device 101A and network device 101D, a tunnel L3 is established between network device 101C and network device 101E, a tunnel L4 is established between network device 101C and network device 101F, a tunnel L5 is established between network device 101D and network device 101E, a tunnel L6 is established between network device 101D and network device 101F, and a tunnel L7 is established between network device 101E and network device 101F. That is, the transmission path 1 includes a tunnel L1 and a tunnel L4, the transmission path 2 includes a tunnel L2 and a tunnel L6, the transmission path 3 includes a tunnel L1, a tunnel L3, and a tunnel L7, and the transmission path 4 includes a tunnel L2, a tunnel L5, and a tunnel L7.

The network devices in the SD-WAN provided by the embodiments of the present application may be managed by one or more control devices. When all the network devices in the SD-WAN are managed by one control device, it means that all the network devices in the SD-WAN are in the same domain. When all the network devices in the SD-WAN are managed by a plurality of control devices, it means that the SD-WAN includes network devices in different domains, and the network devices in different domains are interconnected across domains. The control device manages network devices in the SD-WAN, and comprises: the control device allocates transmission bandwidth and the like to the network device in the SD-WAN. The control device may be a network controller, network analyzer, network management device, gateway or other device having control and analysis capabilities. The control device may be one or more devices.

Fig. 1 illustrates an example in which network devices in an SD-WAN are managed by one control device. As shown in fig. 1, the communication system in the SD-WAN further includes a control device 102. The control device 102 is connected to each network device 101 in the SD-WAN.

Fig. 2 is a schematic structural diagram of another SD-WAN communication system according to an embodiment of the present application. Fig. 2 illustrates an example in which a network device in an SD-WAN is managed by a plurality of network devices. As shown in fig. 2, the communication system in the SD-WAN further includes a plurality of

control devices

102A and 102B. Among them, the control device 102A manages the network devices 101A to 101C, and the control device 102B manages the network devices 101D to 101F. The number of control devices in fig. 2 is for illustrative purposes only and is not intended to limit the communication system in SD-WAN according to the embodiments of the present application.

The routing method in the SD-WAN provided by the embodiment of the application is a data plane-based routing method in the SD-WAN. The network equipment determines path constraint information according to the data message and determines path constraint conditions according to the path constraint information. The network equipment judges whether the network equipment meets the path constraint condition or not; if the network equipment meets the path constraint condition, the network equipment sends an updated data message to the next hop equipment; and if the network equipment does not satisfy the path constraint condition, the network equipment sends a feedback message to the target equipment. When the network device is an entry device for transmitting a data packet in the SD-WAN, the target device may be a control device of the SD-WAN; when the network device is an intermediate device or an egress device for transmitting the data packet in the SD-WAN, the target device is a previous-hop device of the network device.

The following embodiments of the present application take routing of service 1, service 2, and service 3 in an SD-WAN as an example, and describe a routing method in the SD-WAN. Fig. 3 shows the process of selecting path 1 in the SD-WAN for service 1. Fig. 6 shows the process of selecting path 2 in the SD-WAN for service 2. Fig. 7 shows the process of selecting path 3 in the SD-WAN for service 3.

Fig. 3 is a schematic flowchart of a routing method in an SD-WAN according to an embodiment of the present application. The method can be applied to a communication system in SD-WAN as shown in fig. 1 or fig. 2. As shown in fig. 3, the method includes:

step 301, the device 1 obtains path constraint information 1 corresponding to the service 1, where the path constraint information 1 is used to determine a path constraint condition that is satisfied by the path 1 for transmitting the service 1.

The device 1 is an ingress device in the SD-WAN for transmitting a service packet of the service 1, i.e. a first device on the path 1.

In a specific embodiment, the path constraint information 1 includes Service Level Agreement (SLA) information and/or quality of service (QoS) information corresponding to the service 1. The path constraint information 1 specifically includes one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate.

The delay in the path constraint information 1 may be the maximum allowed transmission delay of the traffic 1 on the path 1. Illustratively, the delay may be 150 milliseconds (ms). The jitter in the path constraint information 1 may be the maximum allowable fluctuation range of the transmission delay on each tunnel on the path 1. Illustratively, the jitter may be-0.5 ms to +0.5 ms. The bandwidth in the path constraint information 1 may be a minimum bandwidth of each tunnel on the path 1, and the bandwidth may be a required bandwidth of the service 1. Illustratively, the bandwidth may be 500 megabits per second (mbps). The packet loss rate in the path constraint information 1 may be a maximum allowable packet loss rate of the service 1 on the path 1. Illustratively, the packet loss rate may be 0.5%. The error rate in the path constraint information 1 may be the maximum allowed error rate for the traffic 1 transmitted on the path 1. Illustratively, the bit error rate may be 0.1%. The bandwidth occupancy in the path constraint information 1 may be the maximum allowable bandwidth occupancy of the traffic other than the traffic 1 in each tunnel on the path 1. Illustratively, the bandwidth occupancy may be 30%.

There are various implementation manners for the device 1 to obtain the path constraint information 1 corresponding to the service 1, and the following two implementation manners are taken as examples in the embodiment of the present application to describe.

In a first implementation, the device 1 acquires the path constraint information 1 under the direction of the control device of the SD-WAN. Illustratively, fig. 4 is a flowchart of a method for acquiring the path constraint information 1 by the device 1 according to the embodiment of the present application. As shown in fig. 4, the method may include:

in step 3011A, device 1 receives a routing instruction for service 1 sent by the control device of the SD-WAN.

The routing instruction includes path constraint information 1 or the service type of service 1. The service type of the service 1 may adopt a five-tuple identifier corresponding to the service 1. The quintuple includes a source Internet Protocol (IP) address, a source port, a destination IP address, a destination port, and a transport layer protocol. The transport layer protocol includes Transmission Control Protocol (TCP) or User Datagram Protocol (UDP). The service type of service 1 may also be represented by other information that may uniquely identify service 1.

In an optional embodiment of the present application, when the control device determines that one or more tunnels in the current transmission path of the service 1 do not meet the service requirement of the service 1, a routing instruction may be sent to the device 1.

In a specific embodiment, each network device in the SD-WAN may periodically report the tunnel state information to the control device. Or, each network device in the SD-WAN may report the changed tunnel state information to the control device after the tunnel state information changes. The control device may determine whether the tunnel in the current transmission path satisfies the service requirement of the service 1 based on the received tunnel state information.

In another alternative embodiment of the present application, when the control device receives a routing request for service 1, the control device may send a routing instruction to device 1.

In a specific embodiment, before the SD-WAN starts to transmit the service packet of the service 1, the control device may send a routing instruction for the service 1 to the device 1, so as to detect the transmission path of the service 1 in the SD-WAN in advance.

Step 3012A, device 1 obtains path constraint information 1 according to the routing instruction.

When the routing instruction includes path constraint information 1, the device 1 acquires the path constraint information 1 from the routing instruction. When the selection instruction includes the service type of the service 1, the device 1 determines, according to the service type of the service 1, the locally stored path constraint information 1 corresponding to the service type of the service 1.

In a specific embodiment, the device 1 locally stores a plurality of correspondence between service types and path constraint information. Illustratively, assuming that a quintuple corresponding to the service is used as an identifier of the service type, the path constraint information includes bandwidth and delay. The correspondence between the service types stored in the device 1 and the path constraint information may be as shown in table 1.

TABLE 1

By way of example, assume that the traffic type of traffic 1 included in the routing instruction is characterized as: (IP2, port 1, IP6, port 2, UDP), the device 1 may obtain, based on the correspondence between the service type and the path constraint information shown in table 1, that the path constraint information 1 corresponding to the service 1 is: the bandwidth is 150mbps and the delay is 100 ms.

In a second implementation manner, the device 1 may obtain the path constraint information 1 when receiving the service packet of the service 1. Exemplarily, fig. 5 is a flowchart of a method for acquiring the path constraint information 1 by another device 1 according to the embodiment of the present application. As shown in fig. 5, the method may include:

step 3011B, the device 1 receives the service packet of the service 1 sent by the sending end device.

In a specific embodiment, the sending end device may be a server or a user terminal. The user terminal comprises a mobile phone, wearable equipment, a computer or a notebook computer and the like.

Step 3012B, the device 1 determines, according to the service type of the service packet of the service 1, the locally stored path constraint information 1 corresponding to the service type.

The implementation process of this step can refer to the related explanation of step 3012A, and this embodiment is not described herein again.

In a specific implementation manner, during the message transmission process of the service 1, the device 1 may periodically obtain the path constraint information 1. Alternatively, when the device 1 determines that the current transmission path of the service 1 does not satisfy the service requirement of the service 1, for example, when congestion occurs in one or more network devices on the current transmission path, the device 1 acquires the path constraint information 1. In the embodiment of the present application, the trigger condition for the device 1 to acquire the path constraint information 1 in the message transmission process of the service 1 is not limited.

Step 302, the device 1 determines that it satisfies the path constraint condition corresponding to the path constraint information 1.

In a specific embodiment, when the path constraint information 1 includes a bandwidth, the path constraint condition corresponding to the path constraint information 1 includes: a target tunnel with a bandwidth greater than or equal to that included in the path constraint information 1 exists in a tunnel using the device 1 as an ingress device, and the target tunnel route can reach an egress device in the SD-WAN for transmitting a service packet of the service 1. The target tunnel route can reach the exit device in the SD-WAN for transmitting the service packet of the service 1, and the service packet of the service 1 can be transmitted to the exit device in the SD-WAN for transmitting the service packet of the service 1 through the target tunnel.

After obtaining the path constraint information 1, the device 1 may obtain available bandwidths of all tunnels using the device 1 as an ingress device. When available bandwidth of one or more tunnels exists in the tunnel using the device 1 as the ingress device, and is greater than or equal to the bandwidth included in the path constraint information 1, the device 1 determines that the device 1 satisfies the path constraint condition corresponding to the path constraint information 1.

In a specific embodiment, when the path constraint information 1 does not include bandwidth, the device 1 defaults to satisfy the path constraint condition corresponding to the path constraint information 1. In this case, the device 1 may directly execute step 303 without executing step 302.

Step 303, the device 1 sends the data packet 1 to the device 2 through the tunnel 1.

The device 1 is an entrance device of the tunnel 1 and the device 2 is an exit device of the tunnel 1. The device 2 may be an intermediate device or an egress device in the SD-WAN for transmitting the service packet of the service 1. When the path constraint information 1 includes a bandwidth, the tunnel 1 is: in the tunnel using the device 1 as the ingress device, the available bandwidth is greater than or equal to the bandwidth included in the path constraint information 1, and the route can reach the tunnel of the egress device in the SD-WAN for transmitting the service packet of the service 1. When the path constraint information 1 does not include a bandwidth, the tunnel 1 may be any one of tunnels in which the device 1 is an ingress device and which routes a service packet that can reach an egress device in the SD-WAN for transmitting the service 1.

In a specific embodiment, when the path constraint information 1 includes a time delay, after the device 1 acquires the path constraint information 1, it may acquire all tunnel sets that satisfy the bandwidth included in the path constraint information 1 in the tunnels using the device 1 as the ingress device. The device 1 acquires the tunnel 1 from the tunnel set. After the device 1 sends the data packet to the device 2 through the tunnel 1, the device 1 deletes the tunnel 1 in the tunnel set, thereby avoiding sending the data packet through the same tunnel for multiple times.

In the embodiment of the application, the subsequent tunnel acquisition efficiency can be improved by acquiring the tunnel set comprising all available tunnels in advance, so that the routing efficiency is improved.

In a specific embodiment, the data packet 1 is a service packet or a probe packet. The data packet 1 may carry path constraint information 1. When the path constraint information 1 includes a time delay, the data packet 1 further includes a transmission timestamp for the device 1 to transmit the data packet 1.

In the first case, data packet 1 is a service packet. In the message transmission process of the service 1, after receiving the service message sent by the sending end device, the device 1 may insert the path constraint information 1 into the service message to obtain the data message 1.

In the second case, data message 1 is a probe message. After determining that the device 1 satisfies the path constraint condition corresponding to the path constraint information 1, the device 1 generates a detection message including the path constraint information 1. The probe message is used for detecting a path 1 of a service 1 in the SD-WAN, and the probe message usually does not carry specific service information.

In a specific embodiment, the device 1 may further store a correspondence between the service 1 and the tunnel 1. After the device 1 stores the correspondence between the service 1 and the tunnel 1, when the device 1 receives the service packet of the service 1 again, the tunnel 1 corresponding to the service 1 may be acquired based on the correspondence between the service 1 and the tunnel 1, and the service packet of the service 1 is sent through the tunnel 1. The process of the device 1 storing the correspondence between the service 1 and the tunnel 1 and the process of the device 1 sending the data message 1 to the device 2 through the tunnel 1 can be executed simultaneously; or, the device 1 may first send the data packet 1 to the device 2 through the tunnel 1, and then store the correspondence between the service 1 and the tunnel 1; or, the device 1 may store the corresponding relationship between the service 1 and the tunnel 1, and then send the data packet 1 to the device 2 through the tunnel 1, which is not limited in this embodiment of the application.

Step 304, the device 2 determines the path constraint information 1 corresponding to the service 1 according to the data message 1.

In a first implementation manner, if the data packet 1 includes the path constraint information 1, the device 2 directly obtains the path constraint information 1 from the data packet 1.

In a second implementation, the data packet 1 does not include the path constraint information 1. When the data packet 1 is a service packet, the device 2 determines the locally stored path constraint information 1 corresponding to the service type according to the service type of the service packet. When the data packet 1 is a detection packet, the detection packet includes a service type identifier of the service 1, and the device 2 determines the service type of the service 1 according to the service type identifier, and then determines the locally stored path constraint information 1 corresponding to the service type.

Step 305, the device 2 determines that the device itself does not satisfy the path constraint condition corresponding to the path constraint information 1.

The device 2 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 1, that is, the device 2 determines that it cannot serve as a node on the path 1 for transmitting the service 1.

In the first case, the device 2 is an intermediate device in the SD-WAN for transmitting the service packet of the service 1:

when the path constraint information 1 includes bandwidth, delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the path constraint conditions corresponding to the path constraint information 1 include: a target tunnel meeting the bandwidth included in the path constraint information 1 exists in the tunnel taking the device 2 as an entrance device, and the route of the target tunnel can reach an exit device used for transmitting the service message of the service 1 in the SD-WAN; the actual transmission delay, the actual jitter, the actual packet loss rate, the actual bit error rate and the actual bandwidth occupancy rate of the data packet 1 on the tunnel 1 respectively satisfy the delay, the jitter, the packet loss rate, the bit error rate and the bandwidth occupancy rate included in the path constraint information 1. When a target tunnel meeting the bandwidth included in the path constraint information 1 does not exist in a tunnel using the device 2 as an entry device, the actual transmission delay of the data packet 1 in the tunnel 1 is greater than the delay included in the path constraint information 1, the actual jitter in the tunnel 1 exceeds the jitter range included in the path constraint information 1, the actual packet loss rate in the tunnel 1 is higher than the packet loss rate included in the path constraint information 1, the actual bit error rate in the tunnel 1 is greater than the bit error rate included in the path constraint information 1, and/or the actual bandwidth occupancy rate of other services in the tunnel 1 is greater than the bandwidth occupancy rate included in the path constraint information 1, the device 2 determines that the device 2 does not meet the path constraint condition corresponding to the path constraint information 1.

In the second case, the device 2 is an egress device in the SD-WAN for transmitting the service packet of the service 1:

when the path constraint information 1 includes delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the path constraint conditions corresponding to the path constraint information 1 include: the actual transmission delay, the actual jitter, the actual packet loss rate, the actual bit error rate and the actual bandwidth occupancy rate of the data packet 1 on the tunnel 1 respectively satisfy the delay, the jitter, the packet loss rate, the bit error rate and the bandwidth occupancy rate included in the path constraint information 1. When the actual transmission delay of the data packet 1 in the tunnel 1 is greater than the delay included in the path constraint information 1, the actual jitter in the tunnel 1 exceeds the jitter range included in the path constraint information 1, the actual packet loss rate in the tunnel 1 is higher than the packet loss rate included in the path constraint information 1, the actual error rate in the tunnel 1 is greater than the error rate included in the path constraint information 1, and/or the actual bandwidth occupancy of other services in the tunnel 1 is greater than the bandwidth occupancy included in the path constraint information 1, the device 2 determines that the device does not satisfy the path constraint condition corresponding to the path constraint information 1.

When the path constraint information 1 includes only the bandwidth, the device 2 may default to satisfy the path constraint condition corresponding to the path constraint information 1 by itself. When the device 2 receives the data message 1, it is determined that the routing of the service 1 is completed, and the path 1 for transmitting the service 1 in the SD-WAN is obtained.

For example, in the embodiment of the present application, taking the path constraint information 1 including the time delay as an example, a process of determining, by the device 2, whether or not the device itself meets the path constraint condition corresponding to the path constraint information 1 is described, which includes the following two implementation manners:

in a first implementation, the delay in the path constraint information 1 is the maximum allowed transmission delay of the data packet 1 in the SD-WAN. The data packet 1 further includes a transmission timestamp for the ingress device (device 1 in this embodiment) in the SD-WAN, which is used for transmitting the service packet of the service 1, to transmit the data packet 1. The process of the device 2 determining whether or not it satisfies the path constraint condition corresponding to the path constraint information 1 includes the following steps S11A to S13A:

in step S11A, device 2 obtains the reception timestamp that device 2 received data packet 1.

Illustratively, the receiving timestamp is 2019-11-27-09:49:50:160, which indicates that the time when the device 2 receives the data packet 1 is 09/27/11/2019, 49/50/160 ms.

In step S12A, the device 2 determines that the time difference between the sending timestamp of the data packet 1 sent by the ingress device for transmitting the service packet of the service 1 in the SD-WAN and the receiving timestamp of the data packet 1 received by the device 2 is: and actual transmission delay of the data message 1 from the inlet equipment for transmitting the service message of the service 1 in the SD-WAN to the equipment 2.

Illustratively, the sending time stamp of the data packet 1 sent by the ingress device for transmitting the service packet of the service 1 in the SD-WAN is 2019-11-27-09:49:50:120, and as can be known from the example in step S11A, the actual transmission delay of the data packet 1 from the ingress device for transmitting the service packet of the service 1 in the SD-WAN to the device 2 is 40 ms.

In step S13A, when the actual time delay of the data packet 1 from the ingress device in the SD-WAN for transmitting the service packet of the service 1 to the device 2 is greater than the time delay included in the path constraint information 1, the device 2 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 1.

In the embodiment of the present application, the data packet 1 carries a sending timestamp for the data packet 1 sent by the ingress device used for transmitting the service packet of the service 1 in the SD-WAN, and the sending timestamp is fixed and unchangeable. When the device 2 needs to send a data message to a next hop device, the device 2 can directly forward the data message 1 without changing the sending timestamp carried in the received data message 1, so that the computing resources of the device can be saved.

In a second implementation manner, the delay in the path constraint information 1 is a maximum allowed transmission delay from a previous-hop device (device 1 in this embodiment) of the device 2 in the SD-WAN for the data packet 1 to an egress device in the SD-WAN for transmitting the service packet of the service 1. The data packet 1 further includes a transmission timestamp for the previous hop device to transmit the data packet 1. The process of the device 2 determining whether or not it satisfies the path constraint condition corresponding to the path constraint information 1 includes the following steps S11B to S13B:

in step S11B, the device 2 obtains the reception timestamp of the data packet 1 received by the device 1.

Illustratively, the receive timestamp is 2019-11-27-09:49:50: 160.

In step S12B, the device 2 determines the difference between the sending timestamp of the data packet 1 sent by the previous-hop device and the receiving timestamp of the data packet 1 received by the device 2 as the actual transmission delay of the data packet 1 in the tunnel 1.

Illustratively, the sending time stamp of the data packet 1 sent by the previous-hop device is 2019-11-27-09:49:50:120, and as can be known from the example in step S11A, the actual transmission delay of the data packet 1 on the tunnel 1 is 20 ms.

In step S13B, when the actual transmission delay of the data packet 1 on the tunnel 1 is greater than the delay included in the path constraint information 1, the device 2 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 1.

Step 306, the device 2 sends a feedback message 1 to the device 1, where the feedback message 1 carries the indication information 1.

The indication information 1 is used to indicate to the device 1 that the device 2 cannot be a node on the path 1 for transmitting the traffic 1.

In a specific embodiment, when the tunnel 1 is a bidirectional tunnel, the device 2 sends the feedback message 1 to the device 1 through the tunnel 1. Alternatively, the device 2 may send the feedback packet 1 to the device 1 by using a point-to-point transmission method. The embodiment of the present application does not limit the manner in which the device 2 sends the feedback message 1 to the device 1.

Step 307, the device 1 determines, according to the indication information 1, that the device 2 cannot be used as a node on the path 1 for transmitting the service 1.

In a specific embodiment, the device 1 stores a correspondence between the service 1 and the tunnel 1. After determining that the device 2 cannot serve as a node on the path 1 for transmitting the service 1, the device 1 deletes the correspondence between the service 1 and the tunnel 1, that is, when the device 1 subsequently receives the service packet of the service 1 again, the device 1 does not send the service packet of the service 1 through the tunnel 1.

After device 1 determines that device 2 cannot act as a node on path 1 for transmitting traffic 1, device 1 reselects a downstream device on path 1. In a specific embodiment, when the tunnel with the device 1 as the ingress device includes a tunnel 2 different from the tunnel 1, the following step 308 may be performed. When the path constraint information 1 includes a bandwidth, the tunnel 2 is: in the tunnel using the device 1 as the ingress device, a tunnel which is different from the tunnel 1, has an available bandwidth greater than or equal to the bandwidth included in the path constraint information 1, and is routed to an egress device in the SD-WAN for transmitting the service packet of the service 1. When the path constraint information 1 does not include a bandwidth, the tunnel 1 may be any one of tunnels in which the device 1 is an ingress device, which is different from the tunnel 1 and routes a traffic packet that can reach an egress device in the SD-WAN for transmitting the traffic 1.

Step 308, the device 1 sends the data packet 2 to the device 3 through the tunnel 2.

The device 1 is an entrance device of the tunnel 2 and the device 3 is an exit device of the tunnel 2. The device 3 may be an intermediate device or an egress device in the SD-WAN for transmitting the service messages of the service 1. For the explanation of this step, reference is made to the related explanation of step 303 above, and details of the embodiments of the present application are not repeated herein.

Step 309, the device 3 determines the path constraint information 1 corresponding to the service 1 according to the data message 2.

For the explanation of this step, reference is made to the related explanation of step 304 above, and the description of the embodiments of the present application is omitted here.

In step 310, the device 3 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 1.

For the explanation of this step, reference is made to the related explanation of step 305 above, and the description of the embodiments of the present application is omitted here.

Step 311, the device 3 sends a feedback packet 2 to the device 1, where the feedback packet 2 carries the indication information 2.

The indication information 2 is used to indicate to the device 1 that the device 3 cannot act as a node on the path 1 for transmitting the traffic 1. For the explanation of this step, reference is made to the related explanation of step 306, and the description of the embodiments of the present application is omitted here.

Step 312, the device 1 determines, according to the indication information 2, that the device 3 cannot be used as a node on the path 1 for transmitting the service 1.

For the explanation of this step, reference is made to the related explanation of step 307, and the description of the embodiments of the present application is omitted here.

In a specific embodiment, when the device 1 is used as an ingress device, the egress device, which is used for transmitting the service packet of the service 1 in the SD-WAN, through a route in the tunnel, only includes the tunnel 1 and the tunnel 2; alternatively, when the path constraint information 1 includes a bandwidth, and an available bandwidth in a tunnel using the device 1 as an ingress device is greater than or equal to the bandwidth included in the path constraint information 1, and an egress device for routing a service packet that can reach the SD-WAN and is used for transmitting the service 1 only includes the tunnel 1 and the tunnel 2, the following step 313 may be performed.

Step 313, the device 1 sends a notification message to the control device of the SD-WAN, where the notification message carries the indication information 3.

The indication information 3 is used to indicate to the control device that there is no path 1 in the SD-WAN that can transmit the service 1. In a specific embodiment, the notification message may be a Border Gateway Protocol (BGP) message. For example, when the notification packet is a BGP open (open) message, the indication information 3 may be carried in an optional parameter (optional parameters) field of the BGP open message. The indication information 3 carries the service type of the service 1, and the service type of the service 1 may be encoded by a TLV (type-length-value) and then carried in an optional parameter field of the BGP open message.

In a specific embodiment, after receiving a notification message sent by a device 1, a control device determines a transmission path of a service 1 according to tunnel state information reported by each network device in the SD-WAN, so that the network device in the SD-WAN transmits the service message of the service 1 by using the transmission path determined by the control device; alternatively, the control device stops the assignment of service 1 to the SD-WAN.

Fig. 6 is a schematic flow chart of another routing method in SD-WAN according to the embodiment of the present application. The method can be applied to a communication system in SD-WAN as shown in fig. 1 or fig. 2. As shown in fig. 6, the method includes:

step 601, the device 1 obtains path constraint information 2 corresponding to the service 2, where the path constraint information 2 is used to determine a path constraint condition that the path 2 transmitting the service 2 satisfies.

In a specific embodiment, the path constraint information 2 includes SLA information and/or QoS information corresponding to the service 2. The path constraint information 2 specifically includes one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate. For the explanation of this step, reference may be made to the related explanation of step 301, and details of the embodiment of this application are not repeated herein.

Step 602, the device 1 determines that it satisfies the path constraint condition corresponding to the path constraint information 2.

In a specific embodiment, when the path constraint information 2 does not include bandwidth, the device 1 defaults to satisfy the path constraint condition corresponding to the path constraint information 2. In this case, the device 2 may directly perform step 603 without performing step 602. For the explanation of this step, reference is made to the related explanation of step 302 above, and the description of the embodiments of the present application is omitted here.

Step 603, the device 1 sends the data packet 3 to the device 4 through the tunnel 3.

The device 1 is an entrance device of the tunnel 3 and the device 4 is an exit device of the tunnel 3. For the explanation of this step, reference is made to the related explanation of step 303 above, and details of the embodiments of the present application are not repeated herein.

Step 604, the device 4 determines the path constraint information 2 corresponding to the service 2 according to the data packet 3.

Step 605, the device 4 determines that it satisfies the path constraint condition corresponding to the path constraint information 2.

The device 4 determines that it satisfies the path constraint condition corresponding to the path constraint information 2, that is, the device 4 determines that it can serve as a node on the path 2 for transmitting the service 2.

In the first case, the device 4 is an intermediate device in the SD-WAN for transmitting service packets of the service 2:

when the path constraint information 2 includes bandwidth, delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the path constraint conditions corresponding to the path constraint information 2 include: a target tunnel meeting the bandwidth included in the path constraint information 2 exists in the tunnel taking the device 4 as an entrance device, and the route of the target tunnel can reach an exit device used for transmitting the service message of the service 2 in the SD-WAN; the actual transmission delay, the actual jitter, the actual packet loss rate, the actual bit error rate and the actual bandwidth occupancy rate of the data packet 3 in the tunnel 3 respectively satisfy the delay, the jitter, the packet loss rate, the bit error rate and the bandwidth occupancy rate included in the path constraint information 2. When a target tunnel meeting the bandwidth included in the path constraint information 2 exists in a tunnel using the device 4 as an entry device, the actual transmission delay of the data packet 3 in the tunnel 3 is less than the delay included in the path constraint information 2, the actual jitter in the tunnel 3 is within the jitter range included in the path constraint information 2, the actual packet loss rate in the tunnel 3 is not higher than the packet loss rate included in the path constraint information 2, the actual bit error rate in the tunnel 3 is less than or equal to the bit error rate included in the path constraint information 2, and the actual bandwidth occupancy rate of other services in the tunnel 3 is less than or equal to the bandwidth occupancy rate included in the path constraint information 2, the device 4 determines that the device itself meets the path constraint condition corresponding to the path constraint information 2.

In the second case, the device 4 is an egress device in the SD-WAN for transmitting the service packet of the service 2:

when the path constraint information 2 includes delay, jitter, packet loss rate, bit error rate and bandwidth occupancy, the path constraint conditions corresponding to the path constraint information 2 include: the actual transmission delay, the actual jitter, the actual packet loss rate, the actual bit error rate and the actual bandwidth occupancy rate of the data packet 3 in the tunnel 3 respectively satisfy the delay, the jitter, the packet loss rate, the bit error rate and the bandwidth occupancy rate included in the path constraint information 2. When the actual transmission delay of the data packet 3 in the tunnel 3 is less than or equal to the delay included in the path constraint information 2, the actual jitter in the tunnel 3 is within the jitter range included in the path constraint information 2, the actual packet loss rate in the tunnel 3 is not higher than the packet loss rate included in the path constraint information 2, the actual error rate in the tunnel 3 is less than or equal to the error rate included in the path constraint information 2, and the actual bandwidth occupancy of other services in the tunnel 3 is less than or equal to the bandwidth occupancy included in the path constraint information 2, the device 4 determines that it satisfies the path constraint condition corresponding to the path constraint information 2.

When the path constraint information 2 only includes bandwidth, the device 4 may default that the device itself satisfies the path constraint condition corresponding to the path constraint information 2, and when the device 4 receives the data packet 3, it determines to complete the routing of the service 2, and obtains the path 2 for transmitting the service 2 in the SD-WAN, where the path 2 includes: device 1 to device 4.

The device 4 determines whether it satisfies the implementation process of the path constraint condition corresponding to the path constraint information 2, which may refer to the implementation process related to the device 2 described in step 305 above, and this embodiment is not described herein again.

In the embodiment of the present application, a device 4 is taken as an example of an intermediate device in the SD-WAN for transmitting a service packet of the service 2.

Step 606, the device 4 sends the data packet 4 to the device 5 through the tunnel 4.

The device 4 is an entrance device of the tunnel 4 and the device 5 is an exit device of the tunnel 4. In a specific embodiment, the device 5 may be an intermediate device or an egress device in the SD-WAN for transmitting the service packet of the service 2. For the explanation of this step, reference is made to the related explanation of step 303 above, and details of the embodiments of the present application are not repeated herein.

Step 607, the device 5 determines the path constraint information 2 corresponding to the service 2 according to the data packet 4.

Step 608, the device 5 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 2.

Step 609, the device 5 sends a feedback packet 3 to the device 4, where the feedback packet 3 carries the indication information 4.

The indication information 4 is used to indicate to the device 4 that the device 5 cannot act as a node on the path 2 for transmitting the traffic 2.

In a specific embodiment, when the tunnel 4 is a bidirectional tunnel, the device 5 sends the feedback packet 3 to the device 4 through the tunnel 4. Alternatively, the device 5 may send the feedback packet 3 to the device 4 by using a point-to-point transmission method. The embodiment of the present application does not limit the manner in which the device 5 sends the feedback packet 3 to the device 4.

Step 610, the device 4 determines, according to the indication information 4, that the device 5 cannot be used as a node on the path 2 for transmitting the service 2.

After device 4 determines that device 5 is not a node on path 2 for transmitting traffic 2, device 4 reselects a downstream device on path 2. In a specific embodiment, when the tunnel with the device 4 as the ingress device includes a tunnel 5 different from the tunnel 4, the following step 611 may be performed. When the path constraint information 2 includes a bandwidth, the tunnel 5 is: in the tunnel using the device 4 as the ingress device, a tunnel, which is different from the tunnel 4, has an available bandwidth greater than or equal to the bandwidth included in the path constraint information 2 and is routed to an egress device in the SD-WAN for transmitting the service packet of the service 2. When the path constraint information 2 does not include bandwidth, the tunnel 5 may be any one of tunnels in which the device 4 is an ingress device, which is different from the tunnel 4 and which routes a traffic packet that can reach an egress device in the SD-WAN for transmitting the traffic 2.

Step 611, the device 4 sends the data packet 5 to the device 6 through the tunnel 5.

The device 4 is an entrance device of the tunnel 5 and the device 6 is an exit device of the tunnel 5. The device 6 may be an intermediate device or an egress device in the SD-WAN for transmitting service messages of the service 2. Data packet 5 may be a packet updated based on data packet 4. For the explanation of this step, reference is made to the related explanation of step 303 above, and details of the embodiments of the present application are not repeated herein.

Step 612, the device 6 determines the path constraint information 2 corresponding to the service 2 according to the data packet 5.

Step 613, the device 6 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 2.

Step 614, the device 6 sends a feedback message 4 to the device 4, where the feedback message 4 carries the indication information 5.

The indication information 5 is used to indicate to the device 4 that the device 6 cannot act as a node on the path 2 for transmitting the traffic 2. For the explanation of this step, reference is made to the related explanation of step 306, and the description of the embodiments of the present application is omitted here.

Step 615, the device 4 determines, according to the indication information 5, that the device 6 cannot be used as a node on the path 2 for transmitting the service 2.

In a specific embodiment, when the device 4 is used as an ingress device, the egress device, which is used for routing a service packet that can reach the SD-WAN and is used for transmitting the service 2, only includes the tunnel 4 and the tunnel 5; alternatively, when the path constraint information 2 includes a bandwidth, and an available bandwidth in a tunnel using the device 4 as an ingress device is greater than or equal to the bandwidth included in the path constraint information 2, and an egress device for routing a traffic packet that can reach the SD-WAN and is used for transmitting the traffic 2 only includes the tunnel 4 and the tunnel 5, the following step 616 may be performed.

Step 616, the device 4 sends a feedback message 5 to the device 1, where the feedback message 5 carries the indication information 6.

The indication information 6 is used to indicate to the device 1 that the device 4 cannot act as a node on the path 2 for transmitting the traffic 2.

In a specific implementation manner, after the device 1 receives the feedback message 5, reference may be made to the above step 307 to step 313 for the executed steps, which is not described herein again in this embodiment of the present application.

Fig. 7 is a schematic flowchart of another routing method in SD-WAN according to the embodiment of the present application. The method can be applied to a communication system in SD-WAN as shown in fig. 1 or fig. 2. As shown in fig. 7, the method includes:

step 701, the device 1 obtains path constraint information 3 corresponding to the service 3, where the path constraint information 3 is used to determine a path constraint condition that is satisfied by the path 3 through which the service 3 is transmitted.

In a specific embodiment, the path constraint information 3 includes SLA information and/or QoS information corresponding to the service 3. The path constraint information 3 specifically includes one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate. For the explanation of this step, reference may be made to the related explanation of step 301, and details of the embodiment of this application are not repeated herein.

In the embodiment of the present application, the path constraint information 3 including at least a bandwidth is taken as an example for explanation.

Step 702, the device 1 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 3.

The path constraint conditions corresponding to the path constraint information 3 include: a target tunnel with a bandwidth greater than or equal to that included in the path constraint information 3 exists in the tunnel using the device 1 as an ingress device, and the target tunnel route can reach an egress device in the SD-WAN for transmitting the service packet of the service 3. After obtaining the path constraint information 3, the device 1 may obtain available bandwidths of all tunnels using the device 1 as an ingress device. When there is no tunnel which can reach an egress device for transmitting a service packet of the service 3 in the SD-WAN and has available bandwidth greater than or equal to the bandwidth included in the path constraint information 1 in a tunnel using the device 1 as an ingress device, the device 1 determines that it does not satisfy the path constraint condition corresponding to the path constraint information 3.

Step 703, the device 1 sends a notification message to the control device of the SD-WAN, where the notification message carries the indication information 7.

The indication information 7 is used to indicate to the control device that there is no path 3 in the SD-WAN that can transmit the traffic 3. For the explanation of this step, reference is made to the related explanation of step 313 above, and the description of the embodiments of the present application is omitted here.

The SD-WAN routing method provided in the embodiment of the present application can be used not only for routing a service before transmission of a service packet, but also for enabling a network device to detect whether the network device satisfies a path constraint condition corresponding to a transmitted service during transmission of the service packet.

In a first implementation manner, when receiving a service packet including path constraint information, a device detects whether the device itself satisfies a path constraint condition corresponding to the path constraint information. At this time, the ingress device in the SD-WAN for transmitting traffic needs to insert path constraint information in the received traffic message. In a specific embodiment, the ingress device may insert path constraint information in each received traffic message, or the ingress device may insert path constraint information in the received traffic message according to a predetermined time interval. When the ingress device inserts the path constraint information into each received service message, the ingress device may also insert indication information into each received message, where the indication information is used to indicate whether the path constraint information in the service message is valid.

In a second implementation manner, when receiving a probe packet including path constraint information, a device detects whether the device itself satisfies a path constraint condition corresponding to the path constraint information. At this time, the ingress device in the SD-WAN for transmitting the service does not need to change the received service packet. In a specific embodiment, the ingress device may generate a probe packet including path constraint information according to a predetermined time interval, and send the probe packet to the downstream device according to the predetermined time interval.

In a third implementation, path constraint information is stored in a device located on the transmission path of traffic in the SD-WAN. When receiving a service message including trigger information, the device detects whether the device satisfies a path constraint condition corresponding to the path constraint information. At this time, the ingress device in the SD-WAN for transmitting the service needs to insert trigger information in the received service packet. In a specific embodiment, the ingress device may insert the trigger information into the received traffic message at predetermined time intervals. The trigger information is used for triggering the device to execute the routing process.

In a fourth implementation, path constraint information is stored in a device located on the transmission path of traffic in the SD-WAN. When receiving a detection message including trigger information, the device detects whether the device meets a path constraint condition corresponding to the path constraint information. At this time, the ingress device in the SD-WAN for transmitting the service does not need to change the received service packet. In one specific embodiment, the ingress device may generate a probe packet including trigger information at predetermined time intervals. The trigger information is used for triggering the device to execute the routing process.

In a fifth implementation manner, path constraint information is stored in a device located on a transmission path of a service in the SD-WAN, and the device may periodically detect whether the device itself satisfies a path constraint condition corresponding to the stored path constraint information at predetermined time intervals. At this time, the ingress device in the SD-WAN for transmitting the service does not need to change the received service packet.

In the embodiment of the present application, the service a includes a device a and a device b on a transmission path in the SD-WAN as an example, and the first implementation and the second implementation are exemplarily described. The path constraint information corresponding to the service a is referred to as path constraint information a. The device a is an inlet device for transmitting the service a in the SD-WAN, and the device b is an intermediate device or an outlet device for transmitting the service a in the SD-WAN.

In the first implementation manner, the device a inserts, into each received service message of the service a, path constraint information a and indication information corresponding to the service a, where the indication information is used to indicate whether the path constraint information a is valid. And then, sending the service message of the service a to the device b. After receiving the service message of the service a, if the indication information in the service message indicates that the path constraint information a is valid, the device b detects whether the device b meets the path constraint condition corresponding to the path constraint information a; if the indication information in the service message indicates that the path constraint information a is invalid, the device b forwards the service message by using the corresponding tunnel according to the pre-stored corresponding relationship between the service a and the tunnel. Or, the device a inserts the path constraint information a into the received service message of the service a according to a predetermined time interval, and then sends the service message of the service a to the device b. If the service message received by the device b comprises the path constraint information a, the device b detects whether the device b meets the path constraint condition corresponding to the path constraint information a; if the device b determines that the received service message does not include the path constraint information a, the device b forwards the service message by using the corresponding tunnel according to the pre-stored corresponding relationship between the service a and the tunnel.

In the second implementation manner, the device a generates a probe packet including the path constraint information a according to a predetermined time interval, and sends the probe packet to the device b. When the device b receives the detection message including the path constraint information a, it detects whether the device b meets the path constraint condition corresponding to the path constraint information a.

In a specific implementation manner, in this embodiment, the message used for routing the service in the SD-WAN may be a service message or a probe message of the service. When a message used for selecting a route for a service in the SD-WAN is a service message, the device continues to forward the message regardless of whether the device receiving the message satisfies or does not satisfy the corresponding path constraint condition. When a message used for selecting a route for a service in the SD-WAN is a detection message, if a device receiving the message does not satisfy a path constraint condition corresponding to the service, the device may discard the message, and if the device receiving the message satisfies the path constraint condition corresponding to the service, the device may continue to forward the message.

In this embodiment, a header of the data packet may include a first field and a second field. The first field is used for carrying path constraint information, and the second field is used for indicating whether the path constraint information carried by the first field is valid or not.

In a specific embodiment, the data packet is a service packet. The service message may be a message using an online operation administration and maintenance (IOAM) mechanism. For example, fig. 8 is a schematic structural diagram of a service packet adopting an IOAM mechanism according to an embodiment of the present application. As shown in fig. 8, the service packet includes: an Ethernet header (Ethernet header), an IP header (IP header), a tunnel header (tunnel header), an IOAM extension, and a payload (payload) field. The Ethernet header, the IP header, the tunnel header and the IOAM extension part are all positioned in the message header. The IOAM extension includes a namespace identification (namespace-ID) field, an IOAM information Type (IOAM-E2E-Type) field, and an option data field (option data field determined by IOAM-E2E-Type) field defined by the IOAM information Type field. The name space identification field is used for indicating the service Type, and the IOAM-E2E-Type field is used for indicating the Type of information carried in the option data field determined by IOAM-E2E-Type field.

The value of the IOAM-E2E-Type field may take 0 to 15. Currently, when the value of the IOAM-E2E-Type field is defined to be 0 to 3, the Type of information carried in the option data field determined by IOAM-E2E-Type field is defined. When the value of the IOAM-E2E-Type field is 0, the option data field determined by IOAM-E2E-Type field carries 64-bit serial numbers; when the value of the IOAM-E2E-Type field is 1, the option data field determined by IOAM-E2E-Type field carries a 32-bit serial number; when the IOAM-E2E-Type field takes a value of 2, the indication that the option data field determined by IOAM-E2E-Type field carries a second-level timestamp (timestamp) of 4 bytes; when the IOAM-E2E-Type field takes a value of 3, it indicates that the option data field determined by IOAM-E2E-Type field carries a compressed second time map of 4 bytes. In this embodiment of the present application, it may be defined that, when a value of the IOAM-E2E-Type field is any one of values from 4 to 15, the option data field determined by IOAM-E2E-Type field carries information that is inserted by an ingress device of a service in the SD-WAN in a service message, for example, path constraint information, indication information used for indicating whether the path constraint information is valid, or trigger information used for triggering the device to perform a routing procedure. Illustratively, the value of the IOAM-E2E-Type field is 4, which means that the Option data field determined by IOAM-E2E-Type field carries the information that the ingress device of the service in the SD-WAN inserts in the service message.

In a specific embodiment, referring to fig. 8, the option data field determined by IOAM-E2E-Type field may include a first field for carrying path constraint information. The option data field determined by IOAM-E2E-Type field may further include a second field for indicating whether the path constraint information carried by the first field is valid. The second field may precede the first field. The path constraint information including bandwidth (bandwidth), delay (delay), and jitter (jitter) is exemplified in fig. 8.

The service message shown in fig. 8 may specifically be a VXLAN message, an IPsec message, a GRE message, or the like. Fig. 9 is a schematic structural diagram of a VXLAN packet adopting an IOAM mechanism according to an embodiment of the present application. As shown in fig. 9, the packet header of the VXLAN packet includes an ethernet header, an IP header, a UDP header (UDP header), a VXLAN header, and an IOAM extension. As shown in FIG. 9, the IOAM extension portion also includes an IOAM end-to-end selection (IOAM E2E option) header located before the namespace identification field. The IOAM E2E option header may refer to relevant definitions and explanations in the Internet Engineering Task Force (IETF), and the embodiments of the present application are not described herein again.

In a specific implementation manner, the data packet in the embodiment of the present application is a detection packet. The probe packet may be a reconstructed new packet or a packet extended based on an existing packet (e.g., Bidirectional Forwarding Detection (BFD) packet).

For example, fig. 10 is a schematic structural diagram of a probe packet provided in the embodiment of the present application. The detection message is a reconstructed new message. As shown in fig. 10, the probe packet includes: an ethernet header, an IP header, a UDP header, and an extension. The extension part may include a version (version) field, a type (type) field, a length (length) field, and a data field, among others. The version field is used for indicating a version number, the type field is used for indicating the type of the message, and the length field is used for indicating the length of the data field. The data field includes a first field for carrying path constraint information. The data field may further include a second field for indicating whether the path constraint information carried by the first field is valid.

Further exemplarily, fig. 11 is a schematic structural diagram of another probe packet provided in the embodiment of the present application. The detection message is obtained based on BFD message extension. As shown in fig. 11, the probe packet includes: a mandatory portion and an optional portion. And fields in the optional part of the BFD message can be customized.

In the embodiment of the application, the data field of the optional part of the BFD message is divided into a first field and a second field. The first field is used to carry path constraint information. The second field is used for indicating whether the path constraint information carried by the first field is valid.

The optional part may further include: an authentication type (authentication type) field, an authentication length (authentication ten) field, and an authentication data (authentication data) field. The functions and contents of each field, the authentication type field, the authentication length field, and the authentication data field in the mandatory part may all refer to the relevant definitions in the Remote Function Call (RFC) 5008 communication standard, and the embodiments of the present application are not described herein again.

In this embodiment of the application, the feedback packet may be, for example, a UDP packet or a TCP packet, and may also be a packet in another format for implementing the same function.

For example, fig. 12 is a schematic structural diagram of a feedback packet provided in an embodiment of the present application, where the feedback packet is a UDP packet. As shown in fig. 12, the feedback message includes: an ethernet header, an IP header, a UDP header, and an extension. The extension portion may include, among other things, a version field, a type field, a length field, and a data field. The data field includes: an information field, a tunnel identification field, and a reservation field. The version field is used to indicate a version number. The type field is used to carry indication information for indicating to an upstream device that the device cannot be a node on a path for transmitting traffic. The indication information may be represented by a numerical value, for example, when the value of the type field is 1, it indicates that the device cannot be used as a node on a path for transmitting traffic. The length field is used to indicate the length of the data field. The tunnel identification field is used to carry the identification of the tunnel. The information field is used to carry path constraint information. Illustratively, in the feedback message 1, the value of the type field is 1, the information field carries path constraint information 1, and the tunnel identification field includes an identification of the tunnel 1.

Further exemplarily, fig. 13 is a schematic structural diagram of another feedback packet provided in the embodiment of the present application, where the feedback packet is a TCP packet. As shown in fig. 13, the feedback message includes: ethernet headers, IP headers, TCP headers, and extensions. The extension portion may include, among other things, a version field, a type field, a length field, and a data field. The data field includes: an information field, a tunnel identification field, and a reservation field. The version field is used to indicate a version number. The type field is used to carry indication information for indicating to an upstream device that the device cannot be a node on a path for transmitting traffic. The indication information may be represented by a numerical value, for example, when the value of the type field is 1, it indicates that the device cannot be used as a node on a path for transmitting traffic. The length field is used to indicate the length of the data field. The tunnel identification field is used to carry the identification of the tunnel. The information field is used to carry path constraint information. Illustratively, in the feedback message 1, the value of the type field is 1, the information field carries path constraint information 1, and the tunnel identification field includes an identification of the tunnel 1.

For example, in the embodiment of the present application, taking the data message as the VXLAN message shown in fig. 9 and the feedback message as the UDP message shown in fig. 12 as an example, an implementation process of routing a service in the communication system in the SD-WAN shown in fig. 1 or fig. 2 is described.

The network device 101A in the transmission path 1 is an ingress device for transmitting traffic in the SD-WAN, the network device 101C is an intermediate device for transmitting traffic in the SD-WAN, and the network device 101F is an egress device for transmitting traffic in the SD-WAN. Network device 101A receives a VXLAN message sent by a sending end device, where the VXLAN message includes an ethernet header, an IP header, a UDP header, a VXLAN header, and a payload field. The network device 101A may first obtain the path constraint information, and determine whether itself satisfies the path constraint condition corresponding to the path constraint information according to the path constraint information. When the network device 101A determines that it satisfies the path constraint condition corresponding to the path constraint information, the network device 101A inserts an IOAM extension portion into a VXLAN header in a packet header of a VXLAN packet, sets a value of an IOAM-E2E-Type field of the IOAM extension portion to 4, and adds the path constraint information in an option data field determined by IOAM-E2E-Type field. Network device 101A then sends a VXLAN message including the IOAM extension to network device 101C through tunnel L1. The network device 101C determines whether or not it satisfies the path constraint condition corresponding to the path constraint information according to the path constraint information.

When the network device 101C determines that it satisfies the path constraint condition corresponding to the path constraint information, the network device 101C sends a VXLAN packet including an IOAM extension to the network device 101F through the tunnel L4. The network device 101F determines whether or not it satisfies the path constraint condition corresponding to the path constraint information according to the path constraint information. When the network device 101F determines that it does not satisfy the path constraint condition corresponding to the path constraint information, the network device 101F generates a UDP packet having a type field value of 1, a tunnel identification field including an identification of tunnel L4, and an information field including the path constraint condition, and sends the UDP packet to the network device 101C. Network device 101C determines that network device 101F is not a node on the path to transmit traffic. When a target tunnel (for example, tunnel L3) satisfying the bandwidth included in the path constraint information exists in the tunnel using the network device 101C as the ingress device, the network device 101C sends a VXLAN packet including the IOAM extension to the network device 101E through the tunnel L3. When there is no tunnel satisfying the bandwidth included in the path constraint information in the tunnel using the network device 101C as the ingress device, the network device 101C generates a UDP packet whose type field value is 1, whose tunnel identification field includes an identification of the tunnel L1, and whose information field includes the path constraint condition, and sends the UDP packet to the network device 101A. Network device 101A determines that network device 101C is not capable of acting as a node for traffic traveling on the path. When a target tunnel (for example, tunnel L2) satisfying the bandwidth included in the path constraint information exists in the tunnel using the network device 101A as the ingress device, the network device 101A sends a VXLAN packet including the IOAM extension to the network device 101D through the tunnel L2. When there is no tunnel satisfying the bandwidth included in the path constraint information in the tunnel using the network device 101A as the ingress device, the network device 101A sends a notification packet carrying the indication information to the control device 102 of the SD-WAN, so as to indicate to the control device that there is no path for transmitting the service in the SD-WAN.

When the network device 101C determines that it does not satisfy the path constraint condition corresponding to the path constraint information, the network device 101C generates a UDP packet having a type field value of 1, a tunnel identification field including an identification of the tunnel L1, and an information field including the path constraint condition, and sends the UDP packet to the network device 101A.

Fig. 14 is a flowchart illustrating a routing method in an SD-WAN according to an embodiment of the present application, where a network architecture to which the method is applied includes at least a first device and a second device, and the network architecture may further include a third device, a fourth device, and/or a fifth device. For example, the first device may be, for example, network device 101C shown in fig. 1 or fig. 2, and the second device may be, for example, network device 101A shown in fig. 1 or fig. 2. The network architecture may be, for example, the network architecture shown in fig. 1 or fig. 2. The method may be specifically used to implement the method shown in any one of the embodiments corresponding to fig. 3 to fig. 7. For example, the first device in the method shown in fig. 14 may be device 2 in the method shown in fig. 3, and the second device may be device 1 in the method shown in fig. 3. The method comprises the following steps:

step 1401, a first device receives a first data packet sent by a second device through a first tunnel, where the first device is an egress device of the first tunnel, and the second device is an ingress device of the first tunnel.

Step 1402, the first device determines first path constraint information corresponding to the first service according to the first data packet. The first path constraint information is used for determining a first path constraint condition satisfied by a first path for transmitting a first service.

Step 1403, the first device determines that the first device does not satisfy the first path constraint condition, and the first device sends a first feedback message to the second device. The first feedback message carries first indication information, and the first indication information is used for indicating to the second device that the first device cannot be used as a node for transmitting the first service on the first path.

When the method is specifically used to implement the method embodiment shown in fig. 3, the first device may be, for example, device 2, the second device may be, for example, device 1, the first tunnel may be, for example, tunnel 1, the first data packet may be, for example, data packet 1, and the first feedback packet may be, for example, feedback packet 1. The specific implementation process of steps 1401 to 1403 may refer to the related description in the embodiment shown in fig. 3, and is not described herein again.

In a specific embodiment, the method further comprises: and the first equipment receives a second data message sent by the third equipment through the second tunnel. The first device is an exit device of the second tunnel and the third device is an entry device of the second tunnel. And the first equipment determines second path constraint information corresponding to the second service according to the second data message, wherein the second path constraint information is used for determining a second path constraint condition met by a second path for transmitting the second service. And the first equipment determines that the first equipment meets the second path constraint condition, and forwards the updated second data message to the fourth equipment through the third tunnel. The first device is an entrance device of the third tunnel and the fourth device is an exit device of the third tunnel. When the method is specifically used to implement the embodiment shown in fig. 6, the first device may be, for example, device 4, the second tunnel may be, for example, tunnel 3, the third device may be, for example, device 1, the third tunnel may be, for example, tunnel 4, the fourth device may be, for example, device 5, the second data message may be, for example, data message 3, and the updated second data message may be, for example, data message 4.

In a specific embodiment, the method further comprises: and the first device receives a second feedback message sent by the fourth device, wherein the second feedback message carries second indication information, and the second indication information is used for indicating to the first device that the fourth device cannot be used as a node for transmitting the second service on the second path. And the first equipment determines that the fourth equipment does not meet the second path constraint condition according to the second indication information. When the method is specifically used to implement the embodiment shown in fig. 6, the first device may be, for example, device 4, the fourth device may be, for example, device 5, and the second feedback packet may be, for example, feedback packet 3.

In an optional embodiment of the present application, after the first device determines, according to the second indication information, that the fourth device does not satisfy the second path constraint condition, the method further includes: the first device reselects a downstream device on the second path.

In one embodiment, a first device reselects a downstream device on a second path, comprising: and the first equipment sends the updated second data message to the fifth equipment through the fourth tunnel, wherein the first equipment is the inlet equipment of the fourth tunnel, and the fifth equipment is the outlet equipment of the fourth tunnel. When the method is specifically used to implement the embodiment shown in fig. 6, the first device may be, for example, device 4, the fourth tunnel may be, for example, tunnel 5, the fifth device may be, for example, device 6, and the updated second data message may be, for example, data message 5.

In another optional embodiment of the present application, after the first device determines, according to the second indication information, that the fourth device does not satisfy the second path constraint condition, the method further includes: and the first equipment sends a third feedback message to the third equipment, wherein the third feedback message carries third indication information, and the third indication information is used for indicating the third equipment that the first equipment cannot be used as a node for transmitting the second service on the second path. When the method is specifically used to implement the embodiment shown in fig. 6, the first device may be, for example, device 4, the third device may be, for example, device 1, and the third feedback packet may be, for example, feedback packet 5.

In one implementation, the first data packet is a detection packet, and the detection packet carries first path constraint information.

In this implementation, the receiving, by the first device, the first data packet sent by the second device through the first tunnel includes:

and the first equipment receives the detection message sent by the second equipment through the first tunnel according to a preset time interval.

In another implementation manner, the first data packet is a service packet, and the service packet carries the first path constraint information.

In a specific implementation manner, the determining, by the first device, first path constraint information corresponding to the first service according to the first data packet includes: and the first equipment determines locally stored first path constraint information corresponding to the service type according to the service type of the first data message.

In a specific embodiment, the first path constraint information includes one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate.

In a specific embodiment, a header of the first data packet includes a first field and a second field, where the first field is used to carry the first path constraint information, and the second field is used to indicate whether the first path constraint information carried by the first field is valid.

Fig. 15 is a flowchart illustrating a routing method in an SD-WAN according to an embodiment of the present application, where a network architecture to which the method is applied includes at least a first device and a second device, and the network architecture may further include a third device. For example, the first device may be, for example, 101C shown in fig. 1 or fig. 2, and the second device may be, for example, network device 101A shown in fig. 1 or fig. 2. The network architecture may be, for example, the network architecture shown in fig. 1 or fig. 2. The method may be specifically used to implement the method shown in any one of the embodiments corresponding to fig. 3 to fig. 7. For example, the first device in the method shown in fig. 15 may be device 2 in the method shown in fig. 3, and the second device may be device 1 in the method shown in fig. 3.

Step 1501, the second device sends the first data packet to the first device through the first tunnel, where the second device is an ingress device of the first tunnel, and the first device is an egress device of the first tunnel.

Step 1502, the second device receives a first feedback message sent by the first device, where the first feedback message carries the first indication information.

Step 1503, the second device determines, according to the first indication information, that the first device cannot serve as a node for transmitting the first service on the first path.

Step 1504, the second device sends the second data packet to the third device through the second tunnel, where the second device is an ingress device of the second tunnel, and the third device is an egress device of the second tunnel.

When the method is specifically used to implement the method embodiment shown in fig. 3, the second device may be, for example, device 1, the first tunnel may be, for example, tunnel 1, the first device may be, for example, device 2, the second tunnel may be, for example, tunnel 2, and the third device may be, for example, device 3. The specific implementation process of step 1501 to step 1504 can refer to the related description in the embodiment shown in fig. 3, and is not described herein again.

In a specific embodiment, after the second device sends the second data packet to the third device through the second tunnel, the method further includes: and the second equipment receives a second feedback message sent by the third equipment, wherein the second feedback message carries second indication information. And the second equipment determines that the third equipment can not be used as a node for transmitting the first service on the first path according to the second indication information. And the second equipment sends a notification message to the control equipment, wherein the notification message carries third indication information, and the third indication information is used for indicating that the first path does not exist in the SD-WAN to the control equipment. When the method is specifically used to implement the method embodiment shown in fig. 3, the second device may be, for example, device 1, the second tunnel may be, for example, tunnel 2, the third device may be, for example, device 3, the second data message may be, for example, data message 2, and the second feedback message may be, for example, feedback message 2.

In one implementation, the first data packet and the second data packet are detection packets, and the detection packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting a first service.

In this implementation, after the second device sends the second data packet to the third device through the second tunnel, the method further includes: and the second equipment sends the detection message to the third equipment through the second tunnel according to a preset time interval.

In another implementation manner, the first data packet and the second data packet are service packets, the service packets carry first path constraint information, and the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

In a specific embodiment, the method further comprises: and the second equipment receives the routing instruction which is sent by the control equipment and aims at the first service. And the second equipment acquires first path constraint information according to the routing instruction, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service. When the method is specifically used for implementing the method embodiments shown in fig. 3, fig. 6 or fig. 7 described above, the second device may be, for example, the device 1.

A specific implementation manner, where the routing instruction includes a service type of the first service, and the second device obtains the first path constraint information according to the routing instruction, includes: and the second equipment determines locally-stored first path constraint information corresponding to the service type according to the service type of the first service.

In one embodiment, the routing instruction includes first path constraint information.

In a specific embodiment, the method further comprises: and the second equipment receives the service message of the first service sent by the sending end equipment. The second device determines locally stored first path constraint information corresponding to the service type according to the service type of the service packet of the first service, wherein the first path constraint information is used for determining a first path constraint condition which is satisfied by a first path for transmitting the first service.

In a specific embodiment, the first path constraint information includes one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate or bandwidth occupancy.

At present, a message transmission path in an SD-WAN is determined through network control equipment, on one hand, the instantaneity of the network equipment for acquiring the message transmission path is poor, and the service requirement can not be met for services with higher delay requirements such as video services. On the other hand, for the service transmitted across domains, each domain has a network control device, and the network control device can only determine the message transmission path of the domain managed by the network control device, so that the network control device cannot determine the message transmission path according to the cross-domain scene, and the message transmission path determined by the network control device cannot meet the transmission requirement of the service transmitted across domains.

According to the routing method in the SD-WAN provided by the embodiment of the application, because the control device is not required to select the message transmission path, each network device in the SD-WAN can dynamically select the transmission path in the transmission process of the message, and therefore the routing method can be suitable for the SD-WAN with a large number of network devices and the message transmission of cross-domain transmission services. In addition, in the message transmission process, the network equipment does not need to interact with the control equipment of the SD-WAN, so that the real-time property of message transmission is ensured. Meanwhile, the data transmission quantity between the second equipment and the control equipment is reduced, and the network overhead is reduced.

Fig. 16 is a schematic structural diagram of a routing device in an SD-WAN according to an embodiment of the present application. The second device, which may be applied in the SD-WAN, may be, for example, network device 101A shown in fig. 1 or fig. 2. As shown in fig. 16, the routing device 160 includes:

the transceiver module 1601 is configured to send a first data packet to a first device through a first tunnel, where a second device is an ingress device of the first tunnel, and the first device is an egress device of the first tunnel.

The transceiver module 1601 is further configured to receive a first feedback message sent by the first device, where the first feedback message carries the first indication information.

A processing module 1602, configured to determine, according to the first indication information, that the first device cannot serve as a node on the first path for transmitting the first service.

The transceiver module 1601 is further configured to send a second data packet to a third device through a second tunnel, where the second device is an ingress device of the second tunnel, and the third device is an egress device of the second tunnel.

In a specific implementation manner, the transceiver module 1601 is further configured to receive a second feedback message sent by a third device, where the second feedback message carries second indication information. The processing module 1602 is further configured to determine, according to the second indication information, that the third device cannot serve as a node on the first path for transmitting the first service.

In a specific embodiment, the transceiver module 1601 is further configured to send a notification message to the control device, where the notification message carries third indication information, and the third indication information is used to indicate to the control device that the SD-WAN does not have the first path.

In a specific embodiment, the first data packet and the second data packet are probe packets, and the probe packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting a first service.

In a specific embodiment, the transceiver 1601 is further configured to send a probe packet to the third device through the second tunnel according to a predetermined time interval.

In a specific embodiment, the first data packet and the second data packet are service packets, and the service packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

In a specific embodiment, the transceiver 1601 is further configured to receive a routing instruction sent by the control device for the first service. The processing module 1602 is further configured to obtain first path constraint information according to the routing instruction, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

In a specific embodiment, the routing instruction includes a service type of the first service, and the processing module 1602 is further configured to: and determining locally stored first path constraint information corresponding to the service type according to the service type of the first service.

In a specific implementation manner, the transceiver 1601 is further configured to receive a service packet of a first service sent by a sending end device. The processing module 1602 is further configured to determine, according to the service type of the service packet of the first service, locally stored first path constraint information corresponding to the service type, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

In a particular embodiment, the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate or bandwidth occupancy.

Details not described here can be found in the routing method in the SD-WAN shown in fig. 3, fig. 6, or fig. 7.

In summary, the routing device provided in this embodiment of the present application does not need to control a device to select a packet transmission path, and each network device in the SD-WAN can dynamically select a transmission path in the transmission process of a packet, so that the routing device can be applied to packet transmission of services that are transmitted across domains and SD-WANs with a large number of network devices. In addition, in the message transmission process, the network equipment does not need to interact with the control equipment of the SD-WAN, so that the real-time property of message transmission is ensured. Meanwhile, the data transmission quantity between the second equipment and the control equipment is reduced, and the network overhead is reduced.

Fig. 17 is a schematic structural diagram of another routing device in the SD-WAN according to the embodiment of the present application. The method can be applied to a first device in the SD-WAN, such as the network device 101F or the network device 101C shown in FIG. 1 or FIG. 2, the first device is an egress device or an intermediate device for transmitting traffic in the SD-WAN, and the SD-WAN comprises a plurality of tunnels. As shown in fig. 17, the routing device 170 includes:

the transceiver module 1701 is configured to receive, through a first tunnel, a first data packet sent by a second device, where the first device is an egress device of the first tunnel, and the second device is an ingress device of the first tunnel.

The processing module 1702 is configured to determine, according to the first data packet, first path constraint information corresponding to the first service, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

The transceiver module 1701 is further configured to determine that the transceiver module itself does not satisfy the first path constraint condition, and send a first feedback packet to the second device, where the first feedback packet carries first indication information, and the first indication information is used to indicate, to the second device, that the first device cannot serve as a node for transmitting the first service on the first path.

In a specific embodiment, the transceiver module 1701 is further configured to receive a second data packet sent by a third device through a second tunnel, where the first device is an egress device of the second tunnel, and the third device is an ingress device of the second tunnel.

The processing module 1702 is further configured to determine, according to the second data packet, second path constraint information corresponding to the second service, where the second path constraint information is used to determine a second path constraint condition that is satisfied by a second path for transmitting the second service.

The transceiver module 1701 is further configured to determine that the transceiver module itself meets the second path constraint condition, and forward the updated second data packet to a fourth device through a third tunnel, where the first device is an ingress device of the third tunnel, and the fourth device is an egress device of the third tunnel.

In a specific embodiment, the transceiver module 1701 is further configured to receive a second feedback message sent by the fourth device, where the second feedback message carries second indication information, and the second indication information is used to indicate, to the first device, that the fourth device cannot serve as a node for transmitting the second service on the second path.

The processing module 1702 is further configured to determine, according to the second indication information, that the fourth device does not satisfy the second path constraint condition.

In one specific embodiment, the processing module 1702 is further configured to reselect a downstream device on the second path.

In a specific embodiment, the processing module 1702 is further configured to: and sending the updated second data message to a fifth device through a fourth tunnel, wherein the first device is an inlet device of the fourth tunnel, and the fifth device is an outlet device of the fourth tunnel.

In a specific embodiment, the transceiver module 1701 is further configured to send a third feedback packet to the third device, where the third feedback packet carries third indication information, and the third indication information is used to indicate, to the third device, that the first device cannot serve as a node on the second path for transmitting the second service.

In a specific embodiment, the first data packet is a probe packet, and the probe packet carries first path constraint information.

In one specific embodiment, the transceiver module 1701 is further configured to: and receiving the detection message sent by the second equipment through the first tunnel according to a preset time interval.

In a specific embodiment, the first data packet is a service packet, and the service packet carries first path constraint information.

In one specific embodiment, the processing module 1702 is configured to: and determining locally stored first path constraint information corresponding to the service type according to the service type of the first data message.

In a particular embodiment, the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate.

Details not described here can be referred to in the routing method in the SD-WAN shown in fig. 3 or fig. 6.

Fig. 18 is a block diagram of a routing device 1800 in an SD-WAN according to an embodiment of the present application. The routing device 1800 may be an ingress device, an intermediate device, or an egress device on a transmission path in the SD-WAN, and specifically may be a router or a switch. As shown in fig. 18, the apparatus 1800 includes: a processor 1801 and a memory 1802.

A memory 1802 for storing computer readable instructions;

a processor 1801, configured to invoke the computer-readable instruction, and according to an instruction of the computer-readable instruction, may perform all operations that may be performed by device 2 or device 3 in the method shown in fig. 3, device 4 or device 5 or device 6 in the method shown in fig. 6, or a first device in the method shown in fig. 14; or may also perform all of the operations that may be performed by device 1 in the method shown in fig. 3, device 1 in the method shown in fig. 6, or the second device in the method shown in fig. 15. For example, the operations performed by the device 2 in the embodiment corresponding to fig. 3, or the operations performed by the first device in the embodiment corresponding to fig. 14.

In one particular embodiment, the apparatus 1800 may also include a communication interface 1803. Wherein the memory 1802, the processor 1801, and the communication interface 1803 are communicatively coupled to one another.

Fig. 19 is a block diagram of another alternative routing device 1900 in an SD-WAN according to an embodiment of the present application. The routing device may be an ingress device, an intermediate device, or an egress device on a transmission path in the SD-WAN, and may specifically be a router or a switch. As shown in fig. 19, the apparatus 1900 includes: a communication interface 1901; and a processor 1902 coupled to the communications interface 1901. According to the communication interface 1901 and the processor 1902, the routing apparatus 1900 may perform all the operations that may be performed by the device 2 or the device 3 in the method shown in fig. 3, the device 4 or the device 5 or the device 6 in the method shown in fig. 6, or the first device in the method shown in fig. 14; or may also perform all of the operations that may be performed by device 1 in the method shown in fig. 3, device 1 in the method shown in fig. 6, or the second device in the method shown in fig. 15. The communication interface 1901 is configured to implement transceiving operations, and the processor 1902 is configured to implement operations other than transceiving operations. For example, when the apparatus 1900 is configured to implement the method shown in fig. 14, the communication interface 1901 is configured to receive a first data packet sent by a second device through a first tunnel, and the processor 1902 is configured to determine, according to the first data packet, first path constraint information corresponding to a first service.

In the embodiment of the present application, the processor may be a Central Processing Unit (CPU). The processor may include one or more processing cores, which execute various functional applications and data processing by running a computer program. The processor and the memory are connected by the communication bus.

The processor may further include a hardware chip. The hardware chip may be an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof. In one embodiment, the hardware chip may be used to implement encryption/decryption operations.

The memory may include volatile memory (RAM), such as Random Access Memory (RAM); the memory may also include a non-volatile memory (such as a flash memory), a hard disk (HDD) or a solid-state drive (SSD); the memory may also comprise a combination of memories of the kind described above.

The communication interface may be plural, and the communication interface is used for communication with other devices. The communication interface may include a wired communication interface, a wireless communication interface, or a combination thereof. The wired communication interface may be an ethernet interface, for example. The ethernet interface may be an optical interface, an electrical interface, or a combination thereof. The wireless communication interface may be a Wireless Local Area Network (WLAN) interface, a cellular network communication interface, or a combination thereof.

In the above embodiments, all or part may be implemented by hardware, firmware, or any combination thereof. When software is involved in a particular implementation, it may be embodied in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

In the embodiments of the present application, the terms "first", "second", and "third", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The term "at least one" means one or more, and the term "plurality" means two or more, unless expressly defined otherwise.

The term "and/or" in this application is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

The above description is only exemplary of the present application and is not intended to limit the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims

1. A routing method in a software defined wide area network (SD-WAN), the method comprising:

a first device receives a first data message sent by a second device through a first tunnel, wherein the first device is an exit device of the first tunnel, and the second device is an entrance device of the first tunnel;

the first equipment determines first path constraint information corresponding to a first service according to the first data message, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service;

the first device determines that the first device does not satisfy the first path constraint condition, and the first device sends a first feedback message to the second device, where the first feedback message carries first indication information, and the first indication information is used to indicate, to the second device, that the first device cannot serve as a node on the first path for transmitting the first service.

2. The method of claim 1, further comprising:

the first device receives a second data message sent by a third device through a second tunnel, wherein the first device is an exit device of the second tunnel, and the third device is an entrance device of the second tunnel;

the first equipment determines second path constraint information corresponding to a second service according to the second data message, wherein the second path constraint information is used for determining a second path constraint condition met by a second path for transmitting the second service;

and the first device determines that the first device meets the second path constraint condition, and forwards the updated second data message to a fourth device through a third tunnel, wherein the first device is an inlet device of the third tunnel, and the fourth device is an outlet device of the third tunnel.

3. The method of claim 2, further comprising:

the first device receives a second feedback message sent by the fourth device, where the second feedback message carries second indication information, and the second indication information is used to indicate, to the first device, that the fourth device cannot serve as a node on the second path for transmitting the second service;

and the first equipment determines that the fourth equipment does not meet the second path constraint condition according to the second indication information.

4. The method according to claim 3, wherein after the first device determines that the fourth device does not satisfy the second path constraint condition according to the second indication information, the method further comprises:

the first device reselects a downstream device on the second path.

5. The method of claim 4, wherein the first device reselecting a downstream device on the second path comprises:

and the first device sends the updated second data message to a fifth device through a fourth tunnel, wherein the first device is an entrance device of the fourth tunnel, and the fifth device is an exit device of the fourth tunnel.

6. The method according to claim 3, wherein after the first device determines that the fourth device does not satisfy the second path constraint condition according to the second indication information, the method further comprises:

and the first device sends a third feedback message to the third device, where the third feedback message carries third indication information, and the third indication information is used to indicate, to the third device, that the first device cannot serve as a node on the second path for transmitting the second service.

7. The method according to claim 1, wherein the first data packet is a probe packet, and the probe packet carries the first path constraint information.

8. The method of claim 7, wherein the receiving, by the first device, the first data packet sent by the second device through the first tunnel comprises:

9. The method according to claim 1, wherein the first data packet is a service packet, and the first path constraint information is carried in the service packet.

10. The method according to claim 1, wherein the determining, by the first device, the first path constraint information corresponding to the first service according to the first data packet includes:

and the first equipment determines the locally stored first path constraint information corresponding to the service type according to the service type of the first data message.

11. The method according to any of claims 1 to 10, wherein the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate and bandwidth occupancy rate.

12. The method according to any one of claims 1 to 11, wherein a header of the first data packet includes a first field and a second field, the first field is used for carrying the first path constraint information, and the second field is used for indicating whether the first path constraint information carried by the first field is valid.

13. A routing method in a software defined wide area network (SD-WAN), the method comprising:

a second device sends a first data message to a first device through a first tunnel, wherein the second device is an inlet device of the first tunnel, and the first device is an outlet device of the first tunnel;

the second equipment receives a first feedback message sent by the first equipment, wherein the first feedback message carries first indication information;

the second device determines, according to the first indication information, that the first device cannot serve as a node for transmitting a first service on the first path;

and the second device sends a second data message to a third device through a second tunnel, wherein the second device is an entrance device of the second tunnel, and the third device is an exit device of the second tunnel.

14. The method of claim 13, wherein after the second device sends the second data message to the third device through the second tunnel, the method further comprises:

the second device receives a second feedback message sent by the third device, wherein the second feedback message carries second indication information;

and the second equipment determines that the third equipment can not be used as a node for transmitting the first service on the first path according to the second indication information.

15. The method according to claim 13 or 14, characterized in that the method further comprises:

and the second equipment sends a notification message to the control equipment, wherein the notification message carries third indication information, and the third indication information is used for indicating that the first path does not exist in the SD-WAN to the control equipment.

16. The method according to any one of claims 13 to 15, wherein the first data packet and the second data packet are probe packets, and the probe packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

17. The method of claim 16, wherein after the second device sends the second data message to the third device through the second tunnel, the method further comprises:

and the second equipment sends a detection message to the third equipment through the second tunnel according to a preset time interval.

18. The method according to any one of claims 13 to 15, wherein the first data packet and the second data packet are service packets, and the service packets carry first path constraint information, where the first path constraint information is used to determine a first path constraint condition that is satisfied by a first path for transmitting the first service.

19. The method of any of claims 13 to 18, further comprising:

the second equipment receives a routing instruction which is sent by the control equipment and aims at the first service;

and the second equipment acquires first path constraint information according to the routing instruction, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service.

20. The method of claim 19, wherein the routing instruction includes a service type of the first service, and the second device obtains the first path constraint information according to the routing instruction, including:

and the second equipment determines the locally stored first path constraint information corresponding to the service type according to the service type of the first service.

21. The method of claim 19, wherein the first path constraint information is included in the routing instruction.

22. The method of any of claims 13 to 18, further comprising:

the second device receives a service message of the first service sent by a sending end device;

and the second equipment determines locally-stored first path constraint information corresponding to the service type according to the service type of the service message of the first service, wherein the first path constraint information is used for determining a first path constraint condition met by a first path for transmitting the first service.

23. The method according to any of claims 13 to 22, wherein the first path constraint information comprises one or more of the following information: time delay, jitter, bandwidth, packet loss rate, bit error rate or bandwidth occupancy.

24. The method according to any of claims 13 to 23, wherein a header of the first data packet includes a first field and a second field, the first field is used for carrying the first path constraint information, and the second field is used for indicating whether the first path constraint information carried by the first field is valid.

25. A first device in a software defined wide area network, SD-WAN, comprising:

a communication interface; and

a processor coupled to the communication interface;

the method according to any of claims 1 to 12 is implemented according to the communication interface and the processor.

26. A second device in a software defined wide area network, SD-WAN, comprising:

a communication interface; and

a processor coupled to the communication interface;

the method according to any of claims 13 to 24, implemented according to the communication interface and the processor.

27. A communication system in a software defined wide area network SD-WAN, characterized in that the communication system comprises a first device according to claim 25 and a second device according to claim 26.

28. A computer storage medium having stored thereon instructions which, when executed by a processor, carry out the method of any one of claims 1 to 24.