CN109617805B

CN109617805B - Method and device for acquiring link dynamic attribute and method and device for selecting path

Info

Publication number: CN109617805B
Application number: CN201811566393.7A
Authority: CN
Inventors: 李月光; 蒋文栋
Original assignee: New H3C Technologies Co Ltd Hefei Branch
Current assignee: New H3C Technologies Co Ltd Hefei Branch
Priority date: 2018-12-17
Filing date: 2018-12-17
Publication date: 2022-04-08
Anticipated expiration: 2038-12-17
Also published as: CN109617805A

Abstract

The disclosure provides a method and a device for acquiring link dynamic attributes and a method and a device for selecting a path, which relate to the technical field of network communication, under the scene that the SDN networking contains cloud nodes in a network with unknown quality, transmitting NQA detection configuration to a first interface of a first networking device (upstream networking of the SDN networking) and a second interface of a second networking device (downstream networking of the SDN networking) connected with the cloud nodes to trigger the first networking device and the second networking device to be based on the NQA detection configuration, dynamic attribute detection is carried out on a link formed by the first interface, the cloud node and the second interface, so that the dynamic attribute of the link of the network with unknown quality is obtained, therefore, the quality of the link of the network with unknown quality can be effectively measured, effective reference information is provided for link selection of network service, and the quality of the network service is guaranteed.

Description

Method and device for acquiring link dynamic attribute and method and device for selecting path

Technical Field

The present disclosure relates to the field of network communication technologies, and in particular, to a method and an apparatus for obtaining a link dynamic attribute, and a method and an apparatus for selecting a path.

Background

SDN (Software Defined Network) is a Network scheduled and managed by Software, and is generally a three-layer (i.e., application layer, control layer, and forwarding layer) architecture or a four-layer (i.e., service orchestration layer, application layer, control layer, and forwarding layer) architecture. The SDN controller in the SDN networking is connected with other network equipment in the networking, each network equipment is only responsible for pure data forwarding, and the specific forwarding mode and the service logic are controlled by the SDN controller.

In order to guarantee the service quality of the network service, the SDN controller needs to consider the quality of each link, for example, the quality of the link is represented by a static attribute and a dynamic attribute of the link, where the static attribute includes allocable bandwidth and overhead, and the dynamic attribute includes delay and packet loss rate.

Currently, most SDN networking leases line resources of an operator, and network devices in the SDN networking establish a remote network connection through the line of the operator, thereby implementing a network service across provinces or cities. Due to operator management and control of an operator line, the SDN controller cannot directly acquire the operating parameters of the network device in the operator line, so that the operator line is invisible to the SND controller. The static attributes (i.e., bandwidth, overhead, etc.) of the operator line are usually promised by the operator, and at present, the dynamic attributes of the operator line cannot be known, so that the SDN controller cannot effectively measure the quality of a link including the operator line, thereby affecting network service.

Disclosure of Invention

In view of this, an object of the present disclosure is to provide a method and an apparatus for obtaining a link dynamic attribute, and a method and an apparatus for selecting a path, so as to obtain a dynamic attribute of a link of a network including unknown quality, thereby effectively measuring the quality of the link of the network including unknown quality, and providing effective reference information for link selection of a network service, so as to ensure the quality of the network service.

In order to achieve the above purpose, the technical scheme adopted by the disclosure is as follows:

in a first aspect, the present disclosure provides a method for acquiring a link dynamic attribute, which is applied to an SDN controller, and includes: if the SDN networking contains cloud nodes in a network with unknown quality, acquiring a first interface and a second interface connected with the cloud nodes; the first interface is an interface of first networking equipment in an upstream networking of the SDN networking, and the second interface is an interface of second networking equipment in a downstream networking of the SDN networking; the upstream networking and the downstream networking are respectively positioned at two sides of the network with unknown quality; sending NQA detection configuration to the first interface and the second interface to trigger the first networking equipment and the second networking equipment to perform dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration; the dynamic attributes include: delay and packet loss rate; and acquiring the dynamic attribute of the link detected by the first networking equipment and the second networking equipment.

In a second aspect, the present disclosure provides a path selection method applied to an SDN controller, including: acquiring a path group to be selected from a source node to a destination node of the current service based on the static attribute of each link; the source node and the destination node belong to an upstream networking and a downstream networking of an SDN networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality; acquiring the dynamic attribute of each path to be selected in the path group to be selected, wherein the path to be selected comprises a link; wherein the dynamic attribute of the link of the cloud node in the network containing unknown quality is obtained in advance according to the method of the first aspect; for each path to be selected in the path group to be selected, determining the dynamic attribute of the path to be selected according to the dynamic attribute of each link contained in the path to be selected; and determining the path of the current service based on the dynamic attribute of each path to be selected in the path group to be selected.

In a third aspect, the present disclosure provides an apparatus for obtaining a link dynamic attribute, which is applied to an SDN controller, and includes: the interface acquisition module is used for acquiring a first interface and a second interface which are connected with cloud nodes if the SDN networking contains the cloud nodes in the network with unknown quality; the first interface is an interface of first networking equipment in an upstream networking of the SDN networking, and the second interface is an interface of second networking equipment in a downstream networking of the SDN networking; the upstream networking and the downstream networking are respectively positioned at two sides of the network with unknown quality; the attribute detection module is used for issuing NQA detection configuration to the first interface and the second interface so as to trigger the first networking equipment and the second networking equipment to carry out dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration; the dynamic attributes include: delay and packet loss rate; and the link attribute acquisition module is used for acquiring the dynamic attributes of the links detected by the first networking equipment and the second networking equipment.

In a fourth aspect, the present disclosure provides a path selection apparatus applied to an SDN controller, including: a path acquisition module, configured to acquire a candidate path group from a source node to a destination node of a current service based on a static attribute of each link; the source node and the destination node belong to an upstream networking and a downstream networking of an SDN networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality; the path attribute acquisition module is used for acquiring the dynamic attribute of each path to be selected in the path group to be selected, wherein the path to be selected comprises a link; wherein the dynamic attribute of the link of the cloud node in the network containing unknown quality is obtained in advance according to the method of the first aspect; a path attribute determining module, configured to determine, for each path to be selected in the path group to be selected, a dynamic attribute of the path to be selected according to a dynamic attribute of each link included in the path to be selected; and the path determining module is used for determining the path of the current service based on the dynamic attribute of each path to be selected in the path group to be selected.

In a fifth aspect, the disclosed embodiments provide an SDN controller comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor, the processor executing the machine-executable instructions to implement the above method.

In a sixth aspect, the disclosed embodiments provide a machine-readable storage medium having stored thereon machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the above-described method.

According to the method, the device, the SDN controller and the machine readable storage medium, under the scene that an SDN Network contains a cloud node in a Network with unknown Quality, NQA (Network Quality analysis) detection configuration is issued to a first interface of a first networking device (located in an upstream networking of the SDN Network) and a second interface of a second networking device (a downstream networking of the SDN Network) which are connected with the cloud node, so that the first networking device and the second networking device are triggered to perform dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration, and therefore the dynamic attribute of the link containing the Network with unknown Quality is obtained, the Quality of the link containing the Network with unknown Quality can be effectively measured, effective reference information is provided for link selection of Network service, and the Quality of the Network service is guaranteed.

Additional features and advantages of the disclosure will be set forth in the description which follows, or in part may be learned by the practice of the above-described techniques of the disclosure, or may be learned by practice of the disclosure.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic diagram of a typical SDN networking of an industry vertical network provided by the prior art;

fig. 2 is a schematic flowchart of a method for acquiring a link dynamic attribute according to an embodiment of the present disclosure;

fig. 3 is a schematic diagram of a probe object in a typical SDN networking of an industry vertical network according to an embodiment of the present disclosure;

fig. 4 is a schematic flow chart of a path selection method according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of an apparatus for acquiring a link dynamic attribute according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a path selection device according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an SDN controller according to an embodiment of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the embodiments of the present disclosure will be described clearly and completely with reference to the accompanying drawings, and it is to be understood that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by one of ordinary skill in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

It should be noted that the above method embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.

Currently, most SDN networking leases line resources of an operator, and network devices in the SDN networking establish a remote network connection through the line of the operator, thereby implementing a network service across provinces or cities. Referring to fig. 1, an industry vertical network typical SDN networking is shown, where the SDN networking includes a user private network as an upstream networking and a user private network as a downstream networking, and an operator network; the user private network of the upstream networking and the user private network of the downstream networking are positioned at two sides of the operator network. The operator network includes an Internet network and an MPLS (Multi-Protocol Label Switching) network, and in the embodiment of the present disclosure, a network device in the operator network may be accessed into the SDN network as a cloud node, so as to provide a communication line (i.e., an operator line) to connect an upstream networking and a downstream networking in the SDN network, thereby forming a link including the operator network, such as link province 1_1- > Internet network- > city 1.1 or link province 1_2- > MPLS network- > city 1.2.

At present, the static attribute and the dynamic attribute of an operator line need to be comprehensively considered for measurement of the operator line, and the static attribute of the operator line is usually promised by the operator, so that the static attribute is easy to obtain, but the dynamic attribute of the operator line cannot be known, so that an SDN controller cannot effectively measure the quality of a link containing the operator line, and network service is influenced. Based on this, the embodiments of the present disclosure provide a test method and apparatus for a link dynamic attribute obtaining method, an SDN controller, and a machine-readable storage medium, so as to obtain a dynamic attribute of a link of a network including unknown quality based on NQA detection configuration, thereby effectively measuring the quality of the link of the network including unknown quality, and providing effective reference information for link selection of a network service to ensure the quality of the network service.

It should be noted that, the present invention is only described by taking the quality of the operator network as an example, but it should be understood that the quality of any network with unknown quality can be determined by the method provided in the present embodiment.

Referring to fig. 2, a schematic flow chart of a method for acquiring a link dynamic attribute is shown, where the method is applied to an SDN controller in an SDN networking scenario. As shown in fig. 2, the method comprises the steps of:

step S201, if the SDN networking contains a cloud node in a network with unknown quality, acquiring a first interface and a second interface connected with the cloud node; the first interface is an interface of first networking equipment in an upstream networking of the SDN networking, the second interface is an interface of second networking equipment in a downstream networking of the SDN networking, and the upstream networking and the downstream networking are respectively located on two sides of the network with unknown quality.

In this embodiment, a network (e.g., an operator network) with unknown quality is used as a cloud node, both the upstream networking and the downstream networking belong to a user private network of an SDN networking, and networking devices of the upstream networking and the downstream networking are connected to an SDN controller.

SDN networking is generally industry vertical networking, and horizontal communication requirements do not exist among each networking device, and only vertical communication is used, taking fig. 1 as an example, where the vertical communication includes: note that provinces 1_1 and 1_2 in fig. 1 represent two networking devices in province 1, for example, communication from province to city (a city belonging to the province), city to prefecture (a prefecture belonging to the city), city to province (a prefecture belonging to the city), and prefecture to city (a prefecture belonging to the city).

Wherein, two networking devices in province 1: provinces 1_1 and 1_2 form upstream networking of the SDN networking; the downstream networking comprises: networking device city 1.1 in city 1, networking device city 1.2 in city 2, networking device city 1.3 in city 3, and networking device city 1.4 in city 4 belonging to province 1, and networking device 1.1.1.1 and networking device 1.1.2 in county 1-1 belonging to city 1, networking device 1.2.1 and networking device 1.2.2 in county 2-1 belonging to city 2, networking device 1.3.2 in county 1.3.1 and networking device 1.3.2 in county 3-1 belonging to city 3, networking device 1.4.1 and networking device 1.4.2 in county 4-1 belonging to city 4, and the like.

For convenience of description, a networking device in an upstream networking is referred to as a first networking device, a networking device in a downstream networking is referred to as a second networking device, an interface where the first networking device is connected with the cloud node device is referred to as a first interface, and an interface where the second networking device is connected with the cloud node device is referred to as a second interface. The number of the first interface and the second interface may be one or more, which is not limited in this disclosure, and the first interface and the second interface are generally expressed by a combination of a device identifier and an interface identifier.

Step S202, an NQA detection configuration is issued to the first interface and the second interface to trigger the first networking equipment and the second networking equipment to perform dynamic attribute detection on a link formed by the first interface and the second interface based on the NQA detection configuration.

Wherein the dynamic attributes include: delay time, packet loss rate, etc.

It should be noted that, in this embodiment, it is assumed that there is only one link between two networking devices, that is, between a first networking device and a second networking device (when an NQA detection message is detected, the NQA detection message actually passes through multiple networking devices and multiple links, but does not affect quality detection on a network with unknown quality, so it is assumed that there is only one link between two networking devices here). Since the NQA detection packet passes through the cloud node with unknown quality when performing the NQA detection on the link formed by the first interface and the second interface, the link formed by the first interface, the cloud node, and the second interface is described in this embodiment when describing the link formed by the first interface and the second interface.

The link formed by the first interface, the cloud node and the second interface comprises a link in a first direction formed by the first interface- > the cloud node- > the second interface, and a link in a second direction formed by the second interface- > the cloud node- > the first interface.

For a link in a first direction, a first networking device to which a first interface belongs serves as a source end; and the second networking equipment to which the second interface belongs is used as a destination. The first networking equipment sends an NQA detection message to a second interface of the second networking equipment through the first interface; and after receiving the NQA detection message, the second interface of the second networking equipment generates a corresponding response message and returns the response message to the first interface of the first networking equipment, wherein the response message comprises timestamp information. And the first networking equipment detects and obtains the dynamic attribute of the link in the first direction according to whether the response message is received and the timestamp information in the received response message.

For a link in a second direction, a second networking device to which a second interface belongs is used as a source end; and the first networking equipment to which the first interface belongs is used as a destination. In the detection process, the link in the first direction may be referred to, and finally the second networking device detects the dynamic attribute of the link in the second direction according to the response information returned by the first networking device.

Step S203, acquiring the dynamic attribute of the link detected by the first networking device and the second networking device.

Under the scene that an SDN network contains a cloud node of a network with unknown quality, such as a cloud node in an operator network, an NQA detection configuration is issued to a first interface of a first networking device (located in an upstream networking of the SDN network) and a second interface of a second networking device (located in a downstream networking of the SDN network) connected with the cloud node, so that the first networking device and the second networking device are triggered to perform dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration, and therefore the dynamic attribute of the link containing the operator network is obtained, the quality of the link containing the operator network can be effectively measured, effective reference information is provided for link selection of network service, and the quality of the network service is guaranteed.

The step S201 may be performed when the networking topology changes, or may be performed during the networking and networking process, based on which the step S201 may include:

if the cloud node in the network with unknown quality is detected to be added in the SDN networking, acquiring configuration information of the cloud node; the configuration information comprises a first interface and a second interface configured for the cloud node; generating a detection group corresponding to the network with unknown quality according to the configuration information; wherein the probe group includes a first interface and a second interface. When cloud nodes are increased, a first interface configured for the cloud nodes by a first networking device and a second interface configured for the cloud nodes by a second networking device are obtained in time, the first interface and the second interface are added into a detection group corresponding to a network with unknown quality, and when the link quality is detected, the interfaces in the detection group are used as detection objects, detection configuration is issued in a unified mode, and management and application are facilitated.

In practical applications, the configuration information may be automatically generated according to a configuration operation of a management device of a user at a user side, the configuration information may further include a network with unknown quality, for example, an identifier of a cloud node corresponding to an operator network, one operator network may be regarded as one cloud node, and in order to distinguish different probe groups, the probe group may be named with the identifier of the cloud node.

In a specific implementation process, the SDN controller monitors the addition and deletion of cloud nodes in a network topology graph of the SDN networking in real time. In a possible embodiment, when a user performs a cloud node adding operation by using a management device on the user side, the management device on the user side generates and sends a corresponding adding request and configuration information of a cloud node to be added to an SDN controller; when a user executes cloud node deletion operation by using management equipment on the user side, the management equipment on the user side generates and sends a corresponding deletion request to the SDN controller. And the SDN controller monitors the addition and deletion of cloud nodes in a network topological graph of the SDN networking in real time through the received addition request and deletion request.

For example, when the SDN controller monitors that a cloud node representing an operator network is added to a network topology of a management device of a user side, an interface connected to the cloud node (the interface is an interface on the networking device) is directly acquired through configuration information of the cloud node, and a probe group of the operator network represented by the cloud node is automatically created by taking the interface as a member.

When the SDN controller monitors that a user deletes a cloud node representing an operator network in a network topological graph, deleting configuration information of the cloud node and a detection group corresponding to the cloud node. For example, the SDN controller may delete a locally stored probe group of the operator network characterized by the cloud node and configuration information of the cloud node according to an identifier of the cloud node to be deleted.

Taking fig. 1 as an example, when an Internet cloud node is added, the SDN controller creates a detection group of the cloud node according to configuration information of the Internet cloud node, where members of the detection group include: the interface of the first networking equipment province 1_1, the second networking equipment city 1.1, city 1.2, city 1.3 and the second interface of each networking equipment in city 1.4 of downstream networking; when the Internet cloud node is deleted, the SDN controller deletes the locally stored detection group and configuration information of the Internet cloud node.

In consideration of the fact that in the communication process, a user can increase or delete an interface of an access cloud node according to actual needs, in order to ensure the accuracy of member information in a detection group, when the change of configuration information of the cloud node is detected, the detection group of the cloud node is updated. For example: if the interface G1/0 of the first networking equipment province 1_1 is accessed to the Internet cloud node, the SDN controller automatically adds an interface G1/0 of a member province 1_1 to a detection group of the Internet cloud node; when the interface G1/0 of the first networking device province 1_1 cancels the access to the Internet cloud node, the SDN controller automatically deletes the member interface G1/0 from the probing group of the Internet cloud node. Therefore, unnecessary detection on the deleted interface can be avoided, and the detection efficiency of the link of the network containing unknown quality in the group network can be improved.

In order to further accelerate the detection of the dynamic attributes of all links including networks with unknown quality in the networking and improve the detection efficiency, in a possible embodiment, after the step of generating a detection group corresponding to a network with unknown quality according to the configuration information, the method further includes: the probe objects are generated from the members of the probe group.

For the case where the network of unknown quality is an operator network, for example, 4 members in the probe group are: m1, M2, M3, M4, the generated probe object includes: m1- > M2, M2- > M1, M1- > M3, M3- > M1, M1- > M4, M4- > M1, M2- > M3, M3- > M2, M2- > M4, M4- > M2, M3- > M4, M4- > M3. In consideration of the characteristics of the network topology map of the industry vertical networking (horizontal communication does not need to pass through an operator network), in the process of generating the probe object, only the probe object of the vertical path is generated, that is, the pair combination formed by the first interface of the first networking device in the upstream networking and the second interface of the second networking device in the downstream networking continues with the previous example: assuming that the members M1 and M2 belong to networking devices in an upstream networking, and the members M3 and M4 belong to networking devices in a downstream networking, the probe objects of M1, M2, M3, and M4 are reduced to: m1- > M3, M3- > M1, M1- > M4, M4- > M1, M2- > M3, M3- > M2, M2- > M4 and M4- > M2, and the 12 detection objects are reduced into 8 detection objects, so that the number of the detection objects is reduced, and the operating pressure of an SDN controller is relieved. Based on this, in the step of generating the probe object according to the members of the probe group, the obtained probe object is a directional pair combination formed by the first interface of any first networking device and the second interface of any second networking device accessing the cloud node.

Therefore, after the detection object is obtained, one end of the detection object, which sends information, is used as a source end and one end of the detection object, which receives information, is used as a destination end according to a certain sequence, and orderly detection is performed in sequence, so that the phenomena of missing detection and disordered detection are avoided, and the detection efficiency of all links of networks with unknown quality in the networking is effectively improved.

Referring to a schematic diagram of a detected object in an industry vertical network typical SDN networking shown in fig. 3, the networking structure in fig. 3 is similar to the networking structure in fig. 1, where an Internet network is represented as an Internet cloud node, an MPLS network is represented as an MPLS cloud node, a solid line is used to represent a communication link in the networking, and a bidirectional arrow of the solid line represents that communication of networking devices at two ends of the solid line is bidirectional; the dashed lines are used to indicate the association between the probe objects generated according to the above description, and the dashed double-headed arrows indicate that the interfaces of the networking devices at both ends thereof constitute probe objects that combine to include two directions. That is, for the Internet cloud node, assuming that networking equipment province 1_1, city 1.1, city 1.2, city 1.3 and city 1.4 are all single-interface access cloud nodes, a total of 8 detection objects are generated: interface- > interface of province 1_1- > interface of city 1.1, interface of province 1_1- > interface of city 1.2, interface of province 1_1- > interface of city 1.3, interface of province 1_1- > interface of city 1.4, interface of city 1.1- > interface of city 1_1, interface of city 1.2- > interface of province 1_1, interface of city 1.3- > interface of city 1_1, interface of city 1.4- > interface of city 1_ 1.

Since the dynamic attribute changes with time, in order to detect the dynamic attribute in real time, the step S203 includes: acquiring detection results from the first networking equipment and the second networking equipment according to a set period, or receiving the detection results reported by the first networking equipment and the second networking equipment according to the set period; wherein the detection result comprises the dynamic attribute of the link; and taking the dynamic attribute of the link acquired in the current period as the current dynamic attribute of the link. The set period can be set according to the actual requirement for communication quality, for example, 0.1 ms. By periodically acquiring the dynamic attribute, the real-time performance and the accuracy of the acquired dynamic attribute can be effectively ensured.

In the embodiment of the disclosure, after the dynamic attribute of the link of the network with unknown quality is obtained, the quality of the link of the network with unknown quality can be effectively measured according to the dynamic attribute, so as to provide effective reference information for the link selection of the network service and guarantee the service quality of the network; based on this, the SDN controller may further store the dynamic attribute of the link including the network with unknown quality, so that the link selection is performed in the subsequent process, and the traversal search may be performed directly. The dynamic attributes may be, but not limited to, stored in the form of tables, texts, and graphics, and updated according to a set period.

In the process of providing network service, an SDN controller needs to select an optimal path based on link quality and bandwidth resources so as to perform reasonable traffic scheduling through the optimal path, thereby ensuring the network service quality. Considering that an operator network can generally provide enough bandwidth resources, the path selection based on the bandwidth can be realized, and for the link quality aspect, due to the quality uncertainty brought by the operator network, the selection of the optimal path based on the quality is difficult to realize, so that the reasonable scheduling of the network traffic is influenced, and the network service quality is further influenced. Based on this, on the basis of the above embodiments, the embodiments of the present disclosure further provide a path selection method. The path selection method is applied to an SDN controller, and referring to fig. 4, the method includes the following steps:

step S401, based on the static attribute of each link, a path group to be selected from the source node to the destination node of the current service is obtained.

The source node and the destination node belong to an upstream networking and a downstream networking of an SDN networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality. For example, referring to fig. 3, assume that the source node is province 1_1 and the destination node is county 1.2.1, where province 1_1 belongs to the upstream networking and county 1.2.1 belongs to the downstream networking; namely, the candidate path group from 1_1 province to 1.2.1 county province is selected.

The static attributes of the links may include, but are not limited to, bandwidth, cost, and hop count, where hop count represents the number of links between networking devices associated with any path in the group of paths, and the bandwidth includes remaining allocable bandwidth information. Taking fig. 3 as an example, the hop count of the link from 1.2 in the networking device city to 1.2.1 in county is 1, and the hop count of the link from 1_1 in the networking device city to 1.2 in city is also 1.

In a possible embodiment, the overhead and the bandwidth in the static attribute may be obtained through an interface related to the link, and the overhead and the bandwidth may be default values of the interface or may be set by a user according to actual needs. For example, in the path from province 1_1 to prefecture 1.2.1, the static attribute of the link from node province 1_1 to node city 1.2 may be directly obtained from the interface of the cloud node accessed in province 1_1 and the interface of the cloud node accessed in city 1.2.

Step S402, acquiring a dynamic attribute of each candidate path in the candidate path group, where the candidate path includes a link.

The dynamic attribute of the link of the cloud node in the network including the unknown quality is obtained in advance according to the method for obtaining the dynamic attribute of the link described in the above embodiment.

For convenience of subsequent application, the SDN controller may store, in advance, the obtained dynamic attributes of each link with unknown quality in the networking, by using the above method for obtaining the dynamic attributes of the links. The dynamic attributes of the links containing networks of unknown quality may be obtained from dynamic attribute information stored in the SDN controller. And for the dynamic attribute of the link of the cloud node in the network which does not contain unknown quality, the dynamic attribute of the link can be directly obtained from the interface of networking equipment related to the link.

It should be noted that, if the SDN controller does not find the dynamic attribute of the link, the dynamic attribute of the link is defaulted to meet the quality requirement of the current service, so that when a subsequent path is selected, the link is continuously considered, so as to avoid that multiple paths including the link are not available and the selected path is not the optimal path because the link is directly regarded as not meeting the quality requirement of the current service without acquiring the dynamic attribute.

Step S403, for each candidate path in the candidate path group, determining the dynamic attribute of the candidate path according to the dynamic attribute of each link included in the candidate path.

For each candidate path, determining a link included in the candidate path, and then determining the dynamic attribute of the link included in the candidate path in step S402, thereby determining the dynamic attribute of the candidate path.

For example, the packet loss rate of the dynamic attribute in the candidate path may be specifically calculated by the product of the packet loss rates of the links; the delay of the dynamic attribute in the candidate path may specifically be calculated by summing the delays of the links.

Step S404, determining a path of the current service based on the dynamic attribute of each candidate path in the candidate path group.

And determining the path of the current service according to whether the dynamic attribute of the path to be selected meets the quality requirement.

In the embodiment of the disclosure, for a network with unknown quality in an SDN networking, for example, a path of an operator network, a path group to be selected is selected according to a static attribute of a link; then, the dynamic attribute of the link is determined according to the method for obtaining the dynamic attribute of the link provided by the above embodiment, and the current service path is determined from the path group to be selected based on the dynamic attribute of the link. Therefore, for a scene that the SDN network comprises cloud nodes in the operator network, the dynamic attribute and the static attribute of the link can be considered, so that the path quality comprising the operator network can be effectively measured, the reasonable scheduling of the flow can be realized according to the path quality, and the network service quality is improved.

Considering that in the calculation process of the candidate path group, the static attribute of each link in the SDN networking needs to be traversed for multiple times, in order to reduce the calculation time of the candidate path group as much as possible and improve the calculation efficiency, in a possible implementation, the step S401 includes:

(1) and calculating the optimal path from the source node to the destination node of the current service based on the static attribute and the shortest path algorithm of each link, and storing the optimal path into a path group to be selected.

Considering that the overhead of the link can reflect the network transmission rate more directly, in a possible embodiment, when the optimal path is calculated, the weight of the link is set according to the priority of the overhead and the bandwidth of the link, for example, the weight is distributed according to the overhead of the link, and the smaller the overhead is, the larger the weight is; at this time, if there are a plurality of links of the same weight, the weights of the plurality of links are re-determined according to the bandwidths of the links, the greater the bandwidth, the greater the weight.

After the weight distribution of each link is completed, the optimal path from the source node to the destination node of the current service is calculated in the SDN networking according to a shortest path algorithm, such as dijkstra algorithm, Floyd algorithm or Bellman-Ford algorithm.

The candidate path group is used for storing the calculated candidate paths, and may be, but not limited to, in the form of a set or an array.

(2) And taking the optimal path as a current path, and executing offset path selection operation on the current path. Wherein the offset path selection operation comprises: one link in the current path is forbidden, a suboptimal path from a source node to a destination node is calculated based on the forbidden link and a shortest path algorithm, and the suboptimal path is stored to a path group to be selected.

To facilitate determining whether a link is disabled, an identification bit may be set for each link, and whether the link is disabled may be determined by the identification bit.

Assuming that the optimal path is province 1_1- > Internet cloud node- > city 1.2- > county 1.2.1, the province 1_1- > Internet cloud node in the path is forbidden, and then the suboptimal path from the province 1_1 to the county 1.2.1 is calculated by using the shortest path algorithm again based on the rest links in the networking.

Wherein each time the step of "disabling one link of the current path" is performed, the link to be currently disabled is a link that has not been previously disabled.

(3) Judging whether the number of paths in the path group to be selected is greater than or equal to a preset value, if so, taking the path group to be selected as the path group to be selected of the current service; if not, continuing to execute the offset path selection operation.

If the number of the paths in the path group to be selected is smaller than a preset value, other links of the current path are forbidden, the offset path selection operation is continuously executed by taking the paths from the province 1_1 to the county 1.2.1 as an example, the links from the Internet cloud nodes to the city 1.2 are forbidden, other links are available, and another suboptimal path from the province 1_1 to the county 1.2.1 is calculated based on a short path algorithm.

(4) If the links of the current path are all forbidden, the sub-optimal paths are taken as the current path one by one, and the offset path selection operation is continuously executed until the number of the paths in the path group to be selected is greater than or equal to a preset value, or the path group to be selected comprises all reachable paths from the source node to the destination node.

For example, links in optimal path province 1_1- > Internet cloud node- > city 1.2- > county 1.2.1: 1_1- > Internet cloud node of province, 1.2- > city and 1.2- > county of city are all forbidden, then the obtained suboptimal paths are sequentially used as the current paths, and the offset path selection operation is continuously executed until the quantity requirement is met or the path group to be selected comprises all reachable paths between 1_1 of province and 1.2.1 of county.

By the offset path selection operation, a suboptimal path which is relatively in accordance with the requirements of static attributes and shortest paths can be obtained. When a shortest path algorithm is applied and a suboptimal path between a source node and a destination node is calculated, the reachable path containing the forbidden link is not calculated any more, and only the reachable path not containing the forbidden link is calculated; compared with the mode of calculating all reachable paths to obtain the suboptimal path, the method has the advantages that the calculation time of the suboptimal path is shortened, and the calculation efficiency is improved.

To determine the best path satisfying the quality of service requirement by considering both the dynamic attribute and the static attribute of the path, in a possible embodiment, the step S404 includes: deleting paths of which the dynamic attributes do not meet the service requirements of the current service from the path group to be selected; and selecting a path with the optimal static attribute from the rest paths of the path group to be selected as the path of the current service.

In a specific implementation process, after the dynamic attribute of each candidate route is determined in step S403, the dynamic attribute and the identifier of the corresponding candidate route are stored as a route quality table of the candidate route group. In step S404, the path quality table is searched, and paths whose dynamic attributes do not satisfy the service requirements of the current service are removed from the group of paths to be selected. The path to be selected can be quickly positioned by searching the path quality table, so that the search traversal time is effectively reduced, and the path selection efficiency is improved.

In order to facilitate the path selection, the remaining paths in the path group to be selected are sorted according to the cost and the bandwidth of the paths to obtain a selectable path table. Wherein the cost and bandwidth of the path is determined based on the cost and bandwidth of the links in the path. For example, the links may be sorted according to the priority of the cost and bandwidth of the path, and the path with the minimum cost is used as the path with the optimal static attribute; and when paths with the same cost exist, selecting the path with larger bandwidth as a better path so as to obtain the selectable path table. The cost of the path is the sum of the costs of all links contained in the path, and the bandwidth of the path is the sum of the bandwidths of all the links contained in the path.

In consideration of that in practical application, only one path is needed for service, a path with the optimal static attribute can be directly selected from the selectable path table. And then establishing a communication tunnel according to the path with the optimal static attribute so as to realize the dispatching of the flow.

For the convenience of understanding of the above embodiments, on the basis of the above embodiments, the embodiments of the present disclosure will be described with the SDN networking shown in fig. 3 as an application example.

First, link dynamic attribute obtaining process

And the SDN controller monitors the increase of cloud nodes in a network topology graph of the SDN networking in real time. When monitoring the Internet cloud node added with the Internet network, acquiring configuration information of the Internet cloud node, wherein the configuration information comprises an interface of province 1_1, an interface of city 1.1, an interface of city 1.2, an interface of city 1.3 and an interface of city 1.4. Establishing a detection group of the Internet cloud nodes according to the configuration information, wherein the members of the detection group of the Internet cloud nodes comprise: province 1_1 interface, city 1.1 interface, city 1.2 interface, city 1.3 interface, and city 1.4 interface.

After the detection group of the Internet cloud nodes is obtained, detection objects are generated according to members in the detection group: interface- > interface of province 1_1- > interface of city 1.1, interface of province 1_1- > interface of city 1.2, interface of province 1_1- > interface of city 1.3, interface of province 1_1- > interface of city 1.4, interface of city 1.1- > interface of city 1_1, interface of city 1.2- > interface of province 1_1, interface of city 1.3- > interface of city 1_1, interface of city 1.4- > interface of city 1_ 1.

Similarly, when monitoring the MPLS cloud nodes added with the MPLS network, referring to the Internet cloud nodes, creating a detection group of the MPLS cloud nodes, and generating a detection object: interface- > interface of province 1_2- > interface of city 1.1, interface of province 1_2- > interface of city 1.2, interface of province 1_2- > interface of city 1.3, interface of province 1_2- > interface of city 1.4, interface of city 1.1- > interface of city 1_2, interface of city 1.2- > interface of province 1_2, interface of city 1.3- > interface of city 1_2, and interface of city 1.4- > interface of city 1_ 2.

Respectively issuing NQA detection configuration to networking equipment included in the detection object so as to carry out link detection: and detecting dynamic attributes of the source end- > cloud node- > destination end of the detection object, and storing the obtained dynamic attributes of each detection object into a dynamic attribute list, wherein the dynamic attributes and the link identifiers are stored in the dynamic attribute list in an associated manner.

Second, path selection process

Assuming that the source node is province 1_1 and the destination node is county 1.2.1, a path from province 1_1 to county 1.2.1 is selected to meet the business requirement.

Firstly, according to the static attributes of each link obtained from the interface of each networking device in the networking, assuming that the weight of the link is set according to the overhead and the priority of the bandwidth of the link, calculating the optimal path from 1_1 province to 1.2.1 county by using dijkstra algorithm as follows: province 1_1- > Internet cloud node- > city 1.2- > county 1.2.1.

Setting link province 1_1- > Internet cloud nodes in the optimal path as unavailable, wherein only one link exists between the province 1_1 and the Internet cloud nodes in the graph 3, after the link province 1_1 and the Internet cloud nodes are forbidden, the link province 1_1 and the Internet cloud nodes are broken, the link province 1_1 and the Internet cloud nodes are removed from networking, and then the optimal path is calculated based on dijkstra algorithm again: 1_1- > 1_2- > MPLS cloud- > city 1.2- > county 1.2.1 province.

According to the steps (3) to (4) in the above embodiment, the links Internet cloud node- > city 1.2 and city 1.2- > county 1.1, and province 1_1- > province 1_2, province 1_2- > MPLS cloud, MPLS cloud- > city 1.2 of the suboptimal path in the optimal path are disabled in sequence until the candidate path group includes all reachable paths between province 1_1 and county 1.2.1. The finally obtained candidate path group comprises candidate paths: province 1_1- > Internet cloud node- > city 1.2- > county 1.2.1 and province 1_1- > province 1_2- > MPLS cloud- > city 1.2- > county 1.2.1.

In the candidate path, the link province 1_1- > Internet cloud node- > city 1.2 and the link province 1_2- > MPLS cloud node- > city 1.2 include an operator network, the SDN controller searches a dynamic attribute list stored in the link dynamic attribute obtaining process in advance, and obtains the dynamic attributes of the link province 1_1- > Internet cloud node- > city 1.2 and the link province 1_2- > MPLS cloud node- > city 1.2 from the dynamic attribute list. And the dynamic property of the link city 1.2- > county 1.2.1 which does not contain the operator network in the candidate path can be directly obtained from the interfaces of the city 1.2 and the county 1.2.1.

After the obtained dynamic attribute of each link of the path to be selected is obtained, the packet loss rates of 1_1- > Internet cloud node- > city 1.2- > county 1.2.1 of province are multiplied to obtain the packet loss rate of 1_1- > Internet cloud node- > city 1.2- > county 1.1 of the path province, and the delays of 1_1- > Internet cloud node- > city 1.2- > county 1.1 of province and 1.2- > county 1.2.1 of the path province are added to obtain the delay of 1_1- > Internet cloud node- > city 1.2- > county 1.1 of the path province, so that the dynamic attribute of 1_1- > Internet node- > city 1.2- > county 1.1 of the path province is obtained. Similarly, the dynamic attribute of 1_1- > 1_2- > MPLS cloud- > city 1.2- > county 1.2.1 is obtained through calculation.

And after determining that the two paths to be selected both meet the service requirement of the current service according to the dynamic attributes of the two paths to be selected, sequencing the two paths to be selected according to the cost and the bandwidth of the paths, selecting the path with the minimum cost as the path of the current service, and selecting the path with the maximum bandwidth as the path of the current service when the costs of the two paths are the same.

In correspondence to the above embodiment of the method for acquiring a link dynamic attribute, referring to fig. 5, a schematic structural diagram of an apparatus for acquiring a link dynamic attribute is applied to an SDN controller, and the apparatus includes the following modules:

an interface obtaining module 51, configured to obtain a first interface and a second interface connected to a cloud node if the SDN networking includes the cloud node in the network with unknown quality; the first interface is an interface of first networking equipment in an upstream networking of the SDN networking, and the second interface is an interface of second networking equipment in a downstream networking of the SDN networking; the upstream networking and the downstream networking are respectively positioned at two sides of a network with unknown quality;

the attribute detection module 52 is configured to issue an NQA detection configuration to the first interface and the second interface to trigger the first networking device and the second networking device to perform dynamic attribute detection on a link formed by the first interface and the second interface based on the NQA detection configuration; the dynamic attributes include: delay and packet loss rate;

the link attribute obtaining module 53 obtains the dynamic attributes of the links detected by the first networking device and the second networking device.

Under the scene that the SDN networking contains the cloud node in the network with unknown quality, NQA detection configuration is issued to a first interface of a first networking device (located in the upstream networking of the SDN networking) and a second interface of a second networking device (located in the downstream networking of the SDN networking), which are connected with the cloud node, so that the first networking device and the second networking device are triggered to perform dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration, the dynamic attribute of the link containing the network with unknown quality is obtained, the quality of the link containing the network with unknown quality can be effectively measured, effective reference information is provided for link selection of network service, and the influence of the network service is guaranteed.

The interface obtaining module 51 is further configured to: if the cloud nodes in the network with unknown quality are detected to be added in the SDN networking, acquiring configuration information of the cloud nodes; the configuration information comprises a first interface and a second interface configured for the cloud node; generating a detection group corresponding to the network with unknown quality according to the configuration information; wherein the probe group includes a first interface and a second interface.

The link attribute obtaining module 53 is further configured to: acquiring detection results from the first networking equipment and the second networking equipment according to a set period, or receiving the detection results reported by the first networking equipment and the second networking equipment according to the set period; wherein the detection result comprises the dynamic attribute of the link; and taking the dynamic attribute of the link acquired in the current period as the current dynamic attribute of the link.

Corresponding to the above embodiment of the path selection method, referring to fig. 6, a schematic structural diagram of a path selection device is applied to an SDN controller, and the device includes the following modules:

a path obtaining module 61, configured to obtain a candidate path group from a source node to a destination node of a current service based on a static attribute of each link; the source node and the destination node belong to an upstream networking and a downstream networking of an SDN networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality;

a path attribute obtaining module 62, configured to obtain a dynamic attribute of each candidate path in the candidate path group, where the candidate path includes a link; wherein the dynamic attribute of the link of the cloud node in the network containing unknown quality is obtained in advance according to the method of the first aspect;

a path attribute determining module 63, configured to determine, for each path to be selected in the path group to be selected, a dynamic attribute of the path to be selected according to a dynamic attribute of each link included in the path to be selected;

and a path determining module 64, configured to determine a path of the current service based on the dynamic attribute of each candidate path in the candidate path group.

In the embodiment of the disclosure, for a path of a network with unknown quality in an SDN networking, a path group to be selected is selected according to a static attribute of a link; then, the dynamic attribute of the link is determined according to the method for obtaining the dynamic attribute of the link provided by the above embodiment, and the current service path is determined from the path group to be selected based on the dynamic attribute of the link. Therefore, for a scene of a cloud node in a network with unknown quality in an SDN networking, dynamic attributes and static attributes of a link can be considered, so that the quality of a path with unknown quality can be effectively measured, and further, the reasonable scheduling of flow can be realized according to the quality of the path, and the service quality of the network is improved.

The path obtaining module 61 is further configured to: based on the static attributes and the shortest path algorithm of each link, calculating the optimal path from the source node to the destination node of the current service, and storing the optimal path into a path group to be selected; taking the optimal path as a current path, and executing an offset path selection operation on the current path, wherein the offset path selection operation comprises the following steps: forbidding one link in the current path, calculating a suboptimal path from a source node to a destination node based on the forbidding link and a shortest path algorithm, and storing the suboptimal path to a path group to be selected; judging whether the number of paths in the path group to be selected is greater than or equal to a preset value, if so, taking the path group to be selected as the path group to be selected of the current service; if not, continuing to execute the offset path selection operation; if the links of the current path are all forbidden, the sub-optimal paths are taken as the current path one by one, and the offset path selection operation is continuously executed until the number of the paths in the path group to be selected is greater than or equal to a preset value, or the path group to be selected comprises all reachable paths from the source node to the destination node.

The path determining module 64 is further configured to: deleting paths of which the dynamic attributes do not meet the service requirements of the current service from the path group to be selected; and selecting a path with the optimal static attribute from the rest paths of the path group to be selected as the path of the current service.

The embodiment provides an SDN controller corresponding to the method embodiment. Fig. 7 is a schematic structural diagram of the SDN controller, and as shown in fig. 7, the apparatus includes a processor 1201 and a memory 1202; the memory 1202 is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the above-mentioned link dynamic attribute obtaining method or the above-mentioned path selection method.

The SDN controller shown in fig. 7 further includes a bus 1203 and a communication interface 1204, and the processor 1201, the communication interface 1204 and the memory 1202 are connected through the bus 1203.

The Memory 1202 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Bus 1203 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 7, but this does not indicate only one bus or one type of bus.

The processor 1201 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be implemented by integrated logic circuits of hardware or instructions in the form of software in the processor 1201. The Processor 1201 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present disclosure may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present disclosure may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 1202, and the processor 1201 reads information in the memory 1202 to complete the steps of the method of the foregoing embodiments in combination with hardware thereof.

The embodiment of the present disclosure further provides a machine-readable storage medium, where the machine-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to implement the above message transmission method, and specific implementation may refer to method implementation, and is not described herein again.

The link dynamic attribute obtaining device, the path selecting device, and the SDN controller provided in the embodiments of the present disclosure have the same implementation principle and technical effect as those of the foregoing corresponding method embodiments, and for brief description, reference may be made to corresponding contents in the foregoing method embodiments where no part of the device embodiments is mentioned.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, each functional module or unit in each embodiment of the present disclosure may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method for acquiring link dynamic attributes is applied to an SDN controller, and comprises the following steps:

if the SDN networking contains cloud nodes in a network with unknown quality, acquiring a first interface and a second interface connected with the cloud nodes; the first interface is an interface of a first networking device in an upstream networking of the SDN networking, and the second interface is an interface of a second networking device in a downstream networking of the SDN networking; the upstream networking and the downstream networking are respectively positioned at two sides of the network with unknown quality; the upstream networking and the downstream networking belong to user private networks of the SDN networking, and networking equipment of the upstream networking and the downstream networking are connected with the SDN controller;

issuing NQA detection configuration to the first interface and the second interface to trigger the first networking equipment and the second networking equipment to perform dynamic attribute detection on a link formed by the first interface, the cloud node and the second interface based on the NQA detection configuration;

and acquiring the dynamic attribute of the link detected by the first networking equipment and the second networking equipment.

2. The method of claim 1, wherein if the SDN networking contains a cloud node in a network of unknown quality, the step of obtaining a first interface and a second interface connected to the cloud node comprises:

if the cloud nodes in the network with unknown quality are detected to be added in the SDN networking, acquiring configuration information of the cloud nodes; the configuration information comprises a first interface and a second interface configured for the cloud node;

generating a detection group corresponding to the network with unknown quality according to the configuration information; wherein the probe group includes the first interface and the second interface.

3. The method of claim 1, wherein the step of obtaining that the first networking device and the second networking device detect the dynamic property of the link comprises:

acquiring detection results from the first networking device and the second networking device according to a set period, or receiving the detection results reported by the first networking device and the second networking device according to the set period; wherein the probing result comprises a dynamic property of the link;

and taking the dynamic attribute of the link acquired in the current period as the current dynamic attribute of the link.

4. A path selection method applied to an SDN controller comprises the following steps:

acquiring a path group to be selected from a source node to a destination node of the current service based on the static attribute of each link; the source node and the destination node belong to upstream networking and downstream networking of an SDN (software defined network) networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality;

acquiring the dynamic attribute of each path to be selected in the path group to be selected, wherein the path to be selected comprises a link; wherein the dynamic attribute of the link of the cloud node in the network containing the unknown quality is obtained in advance according to the method of any one of claims 1 to 3;

for each path to be selected in the path group to be selected, determining the dynamic attribute of the path to be selected according to the dynamic attribute of each link contained in the path to be selected;

and determining the path of the current service based on the dynamic attribute of each path to be selected in the path group to be selected.

5. The method according to claim 4, wherein the step of obtaining the candidate path group from the source node to the destination node of the current service based on the static attribute of each link comprises:

based on the static attribute and the shortest path algorithm of each link, calculating the optimal path from the source node to the destination node of the current service, and storing the optimal path into a path group to be selected;

taking the optimal path as a current path, and executing an offset path selection operation on the current path, wherein the offset path selection operation comprises the following steps: forbidding one link in the current path, calculating a suboptimal path from the source node to the destination node based on the forbidding link and a shortest path algorithm, and storing the suboptimal path to the path group to be selected;

judging whether the number of paths in the path group to be selected is greater than or equal to a preset value, if so, taking the path group to be selected as the path group to be selected of the current service; if not, continuing to execute the offset path selection operation;

and if the links of the current path are forbidden, taking the suboptimal path as the current path one by one, and continuing to execute the offset path selection operation until the number of paths in the path group to be selected is greater than or equal to a preset value, or the path group to be selected comprises all reachable paths from the source node to the destination node.

6. The method according to claim 4, wherein the step of determining the path of the current service based on the dynamic attribute of each candidate path in the candidate path group comprises:

deleting paths of which the dynamic attributes do not meet the service requirements of the current service from the path group to be selected;

and selecting a path with the optimal static attribute from the rest paths of the path group to be selected as the path of the current service.

7. An apparatus for acquiring link dynamic attributes, applied to an SDN controller, includes:

the interface acquisition module is used for acquiring a first interface and a second interface which are connected with a cloud node if the SDN network contains the cloud node in the network with unknown quality; the first interface is an interface of a first networking device in an upstream networking of the SDN networking, and the second interface is an interface of a second networking device in a downstream networking of the SDN networking; the upstream networking and the downstream networking are respectively positioned at two sides of the network with unknown quality; the upstream networking and the downstream networking belong to user private networks of the SDN networking, and networking equipment of the upstream networking and the downstream networking are connected with the SDN controller;

an attribute detection module, configured to issue an NQA detection configuration to the first interface and the second interface to trigger the first networking device and the second networking device to perform dynamic attribute detection on a link formed by the first interface, the cloud node, and the second interface based on the NQA detection configuration; the dynamic attributes include: delay and packet loss rate;

and the link attribute acquisition module is used for acquiring the dynamic attribute of the link detected by the first networking equipment and the second networking equipment.

8. The apparatus of claim 7, wherein the interface obtaining module is further configured to:

9. The apparatus of claim 7, wherein the link attribute obtaining module is further configured to:

10. A path selection device applied to an SDN controller comprises:

a path acquisition module, configured to acquire a candidate path group from a source node to a destination node of a current service based on a static attribute of each link; the source node and the destination node belong to upstream networking and downstream networking of an SDN (software defined network) networking respectively, and the upstream networking and the downstream networking are connected through a network with unknown quality;

a path attribute obtaining module, configured to obtain a dynamic attribute of each path to be selected in the path group to be selected, where the path to be selected includes a link; wherein the dynamic attribute of the link of the cloud node in the network containing the unknown quality is obtained in advance according to the method of any one of claims 1 to 3;

a path attribute determining module, configured to determine, for each path to be selected in the path group to be selected, a dynamic attribute of the path to be selected according to a dynamic attribute of each link included in the path to be selected;

and the path determining module is used for determining the path of the current service based on the dynamic attribute of each path to be selected in the path group to be selected.

11. The apparatus of claim 10, wherein the path acquisition module is further configured to acquire the path information

12. The apparatus of claim 10, wherein the path determination module is further configured to:

13. An SDN controller comprising a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor to perform the method of any of claims 1 to 3 or the method of any of claims 4 to 6.

14. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of any of claims 1 to 3 or the method of any of claims 4 to 6.