CN113301071A

CN113301071A - Network source returning method, device and equipment

Info

Publication number: CN113301071A
Application number: CN202010275414.0A
Authority: CN
Inventors: 雷超; 曾福华; 武桂珠
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-04-09
Filing date: 2020-04-09
Publication date: 2021-08-24
Anticipated expiration: 2040-04-09
Also published as: CN113301071B

Abstract

The embodiment of the application provides a method, a device and equipment for returning a source of a network, wherein the method comprises the following steps: obtaining network quality data, wherein the network quality data are used for representing the network quality between a target node and a plurality of upper-level nodes thereof, and the network quality data are obtained by calculation according to the detection result of the network between the target node and the upper-level nodes; and selecting a target upper-level node from the plurality of upper-level nodes according to the network quality data and the load balancing strategy so that the target node can return to the target upper-level node. The method and the device can ensure that the previous-level node with better quality is selected for the node in the source returning process.

Description

Network source returning method, device and equipment

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method, an apparatus, and a device for returning a source to a network.

Background

A Content Delivery Network (CDN) can achieve the purpose of accelerating access by providing a cache node between a user equipment and a source station server.

Currently, the CDN mainly adopts a multi-level cache architecture, taking a two-level cache architecture as an example, a first-level cache node may communicate with the user equipment, and a second-level cache node may communicate with the source station server. The user equipment may request the content from the first-level cache node, and if the content requested by the user equipment is not cached in the first-level cache node, the first-level cache node may request the content from the second-level cache node, which may be understood as the first-level cache node returning to the second-level cache node. Generally, an administrator configures a plurality of second-level cache nodes closer to a first-level cache node according to a distance principle, and a load balancing device controls the first-level cache node to specifically return to which of the plurality of second-level cache nodes the first-level cache node is based on a load balancing policy.

Theoretically, the quality of a network close to a node is generally good, however, an actual network environment is complex and variable, and the network quality between nodes close to each other may be very poor, so how to ensure a back-source process to select a higher-level node with good quality for the node becomes a problem to be solved urgently at present.

Disclosure of Invention

The embodiment of the application provides a method, a device and equipment for returning a source of a network, which are used for solving the problem in the prior art that how to ensure that a previous-level node with better quality is selected for a node in the process of returning the source.

In a first aspect, an embodiment of the present application provides a method for returning a source to a network, where the method includes:

obtaining network quality data, wherein the network quality data are used for representing the network quality between a target node and a plurality of upper-level nodes thereof, and the network quality data are obtained by calculation according to the detection result of the network between the target node and the upper-level nodes;

and selecting a target upper-level node from the plurality of upper-level nodes according to the network quality data and the load balancing strategy so that the target node can return to the target upper-level node.

In a second aspect, an embodiment of the present application provides a method for returning a source to a network, where the method includes:

obtaining probe information indicating a plurality of second nodes for which a network probe of a first node is required;

according to the detection information, detecting the network between the first node and the second node to obtain a detection result, wherein the detection result is used for calculating network quality data, and the network quality data is used for representing the network quality between a target node and a plurality of upper-level nodes thereof;

wherein the first node is the target node, and the second node is the previous-level node; or, the first node is the upper-level node, and the second node is the target node.

In a third aspect, an embodiment of the present application provides a method for returning a source to a network, where the method includes:

acquiring node information, wherein the node information comprises hierarchical relationship information of a plurality of first nodes and a plurality of second nodes;

generating detection information aiming at the plurality of first nodes respectively according to the node information, wherein the detection information of the first nodes is used for indicating a plurality of second nodes aiming at which network detection is needed;

and correspondingly sending the detection information to the plurality of first nodes so that the first nodes can carry out network detection according to the detection information.

In a fourth aspect, an embodiment of the present application provides a source returning device of a network, where the device includes:

the system comprises an obtaining module, a judging module and a judging module, wherein the obtaining module is used for obtaining network quality data, the network quality data are used for representing the network quality between a target node and a plurality of upper-level nodes of the target node, and the network quality data are obtained by calculating according to the detection result of the network between the target node and the upper-level nodes;

and the load balancing module is used for selecting a target upper-level node from the plurality of upper-level nodes according to the network quality data and the load balancing strategy so that the target node can return to the target upper-level node.

In a fifth aspect, an embodiment of the present application provides a source returning device of a network, where the device includes:

an obtaining module, configured to obtain probe information, where the probe information is used to indicate a plurality of second nodes that the first node network needs to target for;

the detection module is used for detecting the network between the first node and the second node according to the detection information to obtain a detection result, wherein the detection result is used for calculating network quality data, and the network quality data is used for representing the network quality between a target node and a plurality of upper-level nodes thereof;

In a sixth aspect, an embodiment of the present application provides a source returning device of a network, where the device includes:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring node information which comprises hierarchical relation information of a plurality of first nodes and a plurality of second nodes;

a generating module, configured to generate, according to the node information, probe information for each of the plurality of first nodes, where the probe information of a first node is used to indicate a plurality of second nodes to which network probing needs to be directed;

and the sending module is used for correspondingly sending the detection information to the plurality of first nodes so that the first nodes can carry out network detection according to the detection information.

In a seventh aspect, an embodiment of the present application provides a computer device, including: a memory, a processor; the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of the first aspects described above.

In an eighth aspect, an embodiment of the present application provides a network node, including: a memory, a processor; the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of the second aspects described above.

In a ninth aspect, an embodiment of the present application provides a computer device, including: a memory, a processor; the memory is configured to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of the third aspects above.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, the computer program comprising at least one code, which is executable by a computer to control the computer to perform the method according to any one of the first aspect.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, the computer program comprising at least one code, which is executable by a computer to control the computer to perform the method according to any one of the second aspect.

Embodiments of the present application also provide a computer-readable storage medium storing a computer program, the computer program comprising at least one code, which is executable by a computer to control the computer to perform the method according to any one of the third aspects.

Embodiments of the present application also provide a computer program, which is used to implement the method according to any one of the first aspect when the computer program is executed by a computer.

Embodiments of the present application also provide a computer program, which is used to implement the method according to any one of the second aspect when the computer program is executed by a computer.

Embodiments of the present application also provide a computer program, which is used to implement the method according to any one of the third aspect when the computer program is executed by a computer.

The network source returning method, the device and the equipment provided by the embodiment of the application can be used for obtaining the network quality data, wherein the network quality data is used for representing the network quality between the target node and a plurality of upper-level nodes thereof, the network quality data is obtained by calculating according to the detection result of the network between the target node and the upper-level nodes obtained by detection, the target upper-level node is selected from the plurality of upper-level nodes according to the network quality data and the load balancing strategy, so that the target node can return to the target upper-level node, the load balancing equipment can determine the target upper-level node which the target node specifically needs to return to the source according to the network quality data between the target node and the upper-level node, and because the network quality data between the target node and the upper-level node is considered when determining the target node specifically returns to which upper-level node, therefore, the back-source process can be ensured to select the superior node with better quality for the node.

Drawings

In order to more clearly illustrate the embodiments of the present application 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 application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1-2 are schematic diagrams of application scenarios according to embodiments of the present application;

fig. 3 is a flowchart illustrating a method for returning a source to a network according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a method for returning a source of a network according to another embodiment of the present application;

fig. 5 is a flowchart illustrating a method for returning a source of a network according to another embodiment of the present application;

fig. 6 is a schematic structural diagram of a source device of a network according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a source device of a network according to another embodiment of the present application;

fig. 9 is a schematic structural diagram of a network node according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a source device of a network according to another embodiment of the present application;

fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a" and "an" typically include at least two, but do not exclude the presence of at least one.

It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B 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 words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.

It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.

In addition, the sequence of steps in each method embodiment described below is only an example and is not strictly limited.

For the convenience of those skilled in the art to understand the technical solutions provided in the embodiments of the present application, a technical environment for implementing the technical solutions is described below.

A source returning method for a network, which is commonly used in the related art, mainly includes that an administrator configures a plurality of second-level cache nodes, which are closer to a first-level cache node, for the first-level cache node according to a distance principle, and a load balancing device controls the first-level cache node to specifically return to which of the plurality of second-level cache nodes, which is closer to the first-level cache node, based on a load balancing policy.

Based on the actual technical requirements similar to those described above, the method for returning the source of the network provided by the application can ensure that the previous-level node with better quality is selected for the node in the process of returning the source by using a technical means.

The source returning mode of the network provided by the embodiments of the present application is specifically described below through an exemplary application scenario.

As shown in FIG. 1, the network may include a primary node 11-1M and a secondary node 21-2N, the primary node 11-1M may be configured to interface with user equipment A, and the secondary node 21-2N may be configured to interface with server B. The secondary node is used as a previous node of the primary node, the primary node can return to the secondary node as required, and the secondary node can further return to the server B as required.

It should be noted that the network architecture in fig. 1 is only an example, and the back-source method provided by the present application may be applied to any type of network that includes multiple levels of nodes and needs to implement back-source of the nodes. For example, the network may specifically be a CDN, and the corresponding node may specifically be a cache node. For another example, in fig. 1, the number of stages of the network is 2, it is understood that the number of stages of the network may also be greater than 2, and the number of stages is 3, for example, the network may further include a third-stage node, which is connected between the second-stage node and the server B, the third-stage node is a previous-stage node of the second-stage node, the second-stage node may return to the third-stage node as needed, and the third-stage node may return to the server B as needed. As another example, a single primary node may be connected to only a portion of the secondary nodes in FIG. 1.

As shown in fig. 1, for a network between a primary node and a secondary node, the primary node may perform network probing according to probing information to obtain a probing result of the network between the primary node and the secondary node, where the probing information is used to indicate a plurality of secondary nodes that the network probing of the primary node needs to be performed on. For example, the primary node 11 may respectively detect the networks between the primary node 11 and the secondary nodes 21 to 2N according to the detection information, so as to obtain the detection result 1 of the networks between the primary node 11 and the secondary nodes 21 to 2N; the primary node 12 can respectively detect the networks between the primary node 12 and the secondary nodes 21-2N according to the detection information to obtain detection results 2 of the networks between the primary node 12 and the secondary nodes 21-2N; … …, the primary node 1M may respectively probe the networks between the primary node 1M and the secondary nodes 21-2N according to the probing information to obtain probing results M of the networks between the primary node 1M and the secondary nodes 21-2N.

For example, a Transmission Control Protocol (TCP) probe may be initiated from a primary node to a secondary node, and specifically, a TCP packet may be sent from the primary node to the secondary node, and the secondary node responds to the TCP packet, so that the primary node may obtain a probe result according to the sent TCP packet and the received response packet. Of course, in other embodiments, the detection result may also be obtained by other detection manners, which is not limited in this application, for example, the primary node may initiate Internet Control Message Protocol (ICMP) detection to the secondary node.

Alternatively, for a network between a primary node and a secondary node, the secondary node may perform network probing according to probing information to obtain a probing result of the network between the primary node and the secondary node, where the probing information is used to indicate a plurality of primary nodes that the network probing of the secondary node needs to target. For example, the secondary node 21 may respectively detect the networks between the primary node 11 and the primary node 1M according to the detection information, so as to obtain the detection results of the networks between the secondary node 21 and the primary node 11 and the primary node 1M; the secondary node 22 may respectively detect the networks between the primary node 11 and the primary node 1M according to the detection information to obtain detection results of the networks between the secondary node 22 and the primary node 11 and the primary node 1M; … …, the secondary node 2N may respectively detect the networks between the primary node 11 and the primary node 1M according to the detection information, so as to obtain the detection results of the networks between the secondary node 2N and the primary node 11 and the primary node 1M.

It should be noted that, in the case that the network further includes a third-level node, similarly, for the network between the second-level node and the third-level node, network probing may be performed by the second-level node or the third-level node to obtain a probing result of the network between the second-level node and the third-level node.

Optionally, there may be multiple types of links between the primary node and the secondary node. Based on the method, network detection can be respectively carried out on the multiple types of links, and detection results for the multiple types of links are obtained. In one embodiment, links may be classified based on network operator, based on which multiple classes of links may correspond to multiple operators. For example, one type of link may correspond to operator 1, one type of link may correspond to operator 2, and one type of link may correspond to operator 3+ operator 2.

For the case that a class of links corresponds to an operator, it may be indicated that a port of the operator of the primary node may be connected to a port of the operator of the secondary node. For the case that a class of links corresponds to multiple operators, it may be indicated that ports of a particular operator of the multiple operators of the primary node may be connected to ports of the multiple operators of the secondary node, for example, ports of operator 3 of the primary node may be connected to ports of operators 2 and 3 of the secondary node.

For example, assume that in the primary node, PU1 and PU4 are ports for carrier 1, PU2 and PU5 are ports for carrier 2, and PU3 is a port for carrier 3; in the secondary node, PI1, PI3 and PI5 are ports of operator 1, PI2 and PI6 are ports of operator 2, and PI4 is a port of operator 3, then the link between the primary node and the secondary node may be as shown in fig. 2. Referring to fig. 2, two types of links exist between the primary node 11 and the secondary node, specifically, a type of link corresponding to the operator 1 and another type of link corresponding to the operator 2, where the type of link corresponding to the operator 1 includes links from the primary node 11 to the secondary node 21, the secondary node 22 and the secondary node 33, and the type of link corresponding to the operator 2 includes links from the primary node 11 to the secondary node 21 and the secondary node 23. A class of link exists between the primary node 12 and the secondary node, and a specific class of link corresponding to the operator 3+ the operator 2 includes links from the primary node 12 to the secondary node 21, the secondary node 22, and the secondary node 33. A class of links exists between the primary node 13 and the secondary node, and a specific class of links corresponding to the operator 1 includes links from the primary node 13 to the secondary node 21, the secondary node 22, and the secondary node 33. A class of links exists between the primary node 14 and the secondary node, and a specific class of links corresponding to the operator 2 includes links from the primary node 13 to the secondary node 21 and the secondary node 33, respectively.

As shown in fig. 1, probe information may be generated by the first computer device 30 and sent to the node that initiated the probe, e.g., the primary node. In one embodiment, the first computer device 30 may specifically be a probe server. For example, the first computer device 30 may generate detection information for respectively detecting the primary node 11 and the primary node 1M and correspondingly send the detection information to the primary node 11 and the primary node 1M, where the node information may include hierarchical relationship information between the primary node 11 and the primary node 1M and between the second node 21 and the secondary node 2N, for example, the secondary node 21 is a node above the primary node 11, and it is understood that in other embodiments, the node above the primary node 11 may not include the secondary node 21.

It should be noted that, for the case where the secondary node initiates the probing, the first computer device 30 may generate the probing information for probing the primary node respectively by the secondary node 21 to the secondary node 2N according to the node information, and correspondingly send the probing information to the secondary node 21 to the secondary node 2N.

It should be noted that, in the case that the network further includes a third-level node, the second-level node or the third-level node may initiate detection on the network between the second-level node and the third-level node, for example, the second-level node initiates detection, and the first computer device 30 may generate detection information on the detection of the third-level connection of the second-level node 21 to the second-level node 2N according to the node information, and correspondingly send the detection information to the second-level node 21 to the second-level node 2N.

After the probing result is obtained, the probing result may be sent to the quality computing device 40, and the network quality data is obtained by the quality computing device 40 according to the probing result. Illustratively, the quality computing device 40 may obtain, according to the detection results 1 of the networks between the primary nodes 11 and the secondary nodes 21 to 2N, network quality data 1 representing the network quality between the primary nodes 11 and the secondary nodes 21 to 2N, respectively; the quality computing device 40 can correspondingly obtain network quality data 2 representing the network quality between the primary node 12 and the secondary nodes 21-2N according to the detection results 2 of the networks between the primary node 12 and the secondary nodes 21-2N respectively; … …, the quality calculating device 40 may obtain the network quality data M representing the network quality between the primary node 1M and the secondary nodes 21-2N according to the detection results M of the network between the primary node 1M and the secondary nodes 21-2N, respectively.

Alternatively, the network quality data may be obtained by the node (e.g., the primary node) that obtained the probe result based on the probe result; alternatively, the network quality data may be derived by a device other than the quality computing device based on the probing results.

It should be noted that, under the condition of multiple types of links, network quality data for the multiple types of links between a single primary node and a single secondary node can be obtained based on the detection results of the multiple types of links between the single primary node and the single secondary node.

After the quality computing device 40 obtains the network quality data, as shown in fig. 1, the quality computing device 40 may send the network quality data to the second computer device 50, and the second computer device 50 selects a target secondary node for the primary node from the plurality of secondary nodes according to the load balancing policy and the network quality data between the primary node and the secondary nodes, so that the primary node can return to the target secondary node. In one embodiment, the second computer device 50 may specifically be a load balancing device.

For example, the second computer device 50 may select a target secondary node for the primary node 11 according to the load balancing policy and the network quality data 1; the second computer device 50 may select a target secondary node for the primary node 12 based on the load balancing policy and the network quality data 2; … …, the second computer device 50 may select a target secondary node for the primary node 1M based on the load balancing policy and the network quality data M.

It will be appreciated that where the network further includes tertiary nodes, a target tertiary node may be selected for the secondary node from the plurality of tertiary nodes by the second computer device 50 based on the load balancing policy and the network quality data between the secondary and tertiary nodes so that the secondary node can be sourced back to the target tertiary node.

Since the second computer device 50 considers the network quality data between the primary node and the secondary node when determining to which secondary node the primary node is specifically sourced, it can be ensured that the source returning process selects the superior node with better quality for the node.

As shown in fig. 1, after the second computer device 50 selects the target secondary node for the first-level node 11-the first-level node 1M, the second computer device 50 may configure the corresponding relationship between the first-level node and the target secondary node thereof into a Domain Name System (DNS) server 60, and the DNS server 60 may indicate the target secondary node corresponding to the first-level node when the first-level node requests the second-level node which needs to be returned to the source, so that the first-level node can be returned to the target secondary node. Since the load status of the node dynamically changes, the correspondence relationship that the load balancing device configures to the DNS server 60 also changes according to the load status.

Alternatively, the second computer device 50 may configure its corresponding secondary node to the primary node so that the primary node may determine the secondary nodes that need to be returned to the source based on the configuration.

As shown in fig. 1, after the second computer device 50 configures the corresponding relationship between the primary node and the target secondary node thereof to the DNS server 60, taking the CDN network as an example, assuming that the user equipment a requests content from the primary node 1M, the primary node 1M may first determine whether the content requested by the user equipment a is cached locally according to the request of the user equipment a, and if the primary node 1M determines that the content requested by the user equipment a is cached, the primary node 1M may directly return the content requested by the user equipment a to the user equipment a. If level one node 1M determines that it does not cache the content requested by user device A, user device A may request the DNS server 60 for a level two node that it needs to come back to the source. The DNS server 60 may determine which secondary node the primary node 1M needs to return to the source through the corresponding relationship configured by the second computer device 50, that is, determine the target secondary node.

Further, assuming that the determined target secondary node is the secondary node 2N, the DNS server 60 may indicate the secondary node 2N to the primary node 1M, and the primary node 1M may request the content from the secondary node 2N according to the indication of the DNS server 60. The second-level node 2N first determines whether the content requested by the first-level node 1M is cached locally according to the request of the first-level node 1M, and if the second-level node 2N determines that the content requested by the first-level node 1M is cached locally, the second-level node 2N may directly return the content requested by the first-level node 1M to the first-level node 1M, and the first-level node 1M may locally cache the content and return the content to the user equipment a. If the second level node 2N determines that the content requested by the first level node 1M is not cached, the second level node 2N may request the content from the server B, locally cache and return the content to the first level node 1M after obtaining the content, and the first level node 1M may locally cache and return the content to the user equipment a after receiving the content returned by the second level node 2N.

It should be noted that, in fig. 1, the first computer device and the second computer device are taken as different devices as an example, and it is understood that, in practical applications, the first computer device and the second computer device may also be the same device, that is, one device performs the functions of load balancing and generating the detection information.

In fig. 1, the quality computing device and the second computing device are taken as different devices as an example, and it is understood that in practical applications, the quality computing device and the second computing device may also be the same device, that is, one device performs the functions of load balancing and obtaining network quality data according to the detection result.

In fig. 1, the second computing device and the DNS server are taken as different devices as an example, and it is understood that in practical applications, the second computing device and the DNS server may also be the same device, that is, one device performs the functions of load balancing and DNS server.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.

Fig. 3 is a flowchart illustrating a method for returning a source of a network according to an embodiment of the present application, where an execution subject of the embodiment may be the second computer device 50 in fig. 1. As shown in fig. 3, the method of this embodiment may include:

301, obtaining network quality data, where the network quality data is used to characterize network quality between a target node and a plurality of previous nodes thereof, and the network quality data is obtained by calculation according to a detection result of a network between the target node and the previous nodes;

step 302, selecting a target previous-level node from the plurality of previous-level nodes according to the network quality data and a load balancing strategy, so that the target node can return to the target previous-level node.

In the embodiment of the present application, referring to fig. 1, the target node may specifically be a first-level node, and the previous-level node may specifically be a second-level node. In a scenario that a network further includes a third-level node, the target node may also be a second-level node, and the corresponding previous-level node may specifically be a third-level node. In a scenario that a network further includes a fourth-level node, the target node may also be a third-level node, and the corresponding previous-level node may specifically be a fourth-level node; … …, and so on. For convenience of explanation, the target node is mainly taken as a first-level node as an example in the following.

In one embodiment, second computer device 50 may receive the network quality data sent by quality computing device 40. Referring to fig. 1, the network quality data may specifically include the aforementioned network quality data 1 to network quality data M.

In another embodiment, the second computer device 50 may receive the network quality data sent by the node initiating probing according to its probing result, referring to fig. 1, the node initiating probing may be a primary node or a secondary node, and the network quality data may include the aforementioned network quality data 1 to network quality data M. Taking the node initiating the detection as a primary node as an example, the primary node 11 may detect the network between the primary node and the secondary node to obtain a detection result 1, calculate to obtain network quality data 1 according to the detection result 1, and send the network quality data 1 to the second computer device 50; the primary node 12 detects the network between the primary node and the secondary node to obtain a detection result 2, calculates the network quality data 2 according to the detection result 2 and sends the network quality data 2 to the second computer device 50; … …, the first level node 1M detects the network between itself and the second level node to obtain the detection result M, and calculates the network quality data M according to the detection result M and sends it to the second computer device 50.

In yet another embodiment, the second computer device 50 may receive the probing result sent by the node initiating the probing, and calculate the network quality data according to the probing result. Referring to fig. 1, taking a node initiating probing as a primary node as an example, the second computer device 50 may receive a probing result 1 obtained by probing by the primary node 11, and calculate to obtain network quality data 1 according to the probing result 1; the second computer device 50 may receive the detection result 2 detected by the primary node 12, and calculate the network quality data 2 according to the detection result; … …, the second computer device 50 may receive the detection result M detected by the first-level node 1M, and calculate the network quality data M according to the detection result M.

Taking the example that the node a probes the network between the node a and the node b, the probing result of the node a for the node b may include: the number of TCP packets sent by the node a to the node b and the number of response packets returned by the node b to the node a, for example, 10 TCP packets are sent by the node a to the node b, and only 9 response packets are returned by the node b to the node a. For example, the probing result of node a for node b may include: the node a sends the packet loss rate of the TCP packet to the node b, for example, if the node a sends 10 TCP packets to the node b, and the node b only returns 9 response packets to the node a, the packet loss rate is 10%. For example, the probing result of node a for node b may include: Round-Trip Time (RTT) of the TCP packet, for example, if the node a sends 10 TCP packets to the node b, and the node b only returns 9 response packets to the node a, the detection result may include the Round-Trip Time of each of the 9 TCP packets that receive the response packet. Of course, in other embodiments, the detection result may also include other types of data, which is not limited in this application.

It can be understood that the higher the packet loss rate is, the worse the network quality is, and the lower the packet loss rate is, the better the network quality is; a smaller RTT may indicate better network quality, and a larger RTT may indicate worse network quality. Based on this, the network quality data can be obtained from the packet loss rate and/or RTT. The network quality data may be, for example, a network quality level, and of course, in other embodiments, the network quality data may also be other forms of data, which is not limited in this application.

Taking the example of obtaining the network quality data by calculating according to the packet loss rate, the network quality level matched with the packet loss rate can be obtained according to the packet loss rate of the network between the node a and the node b and the corresponding relationship between different packet loss rate ranges and the network quality levels, so as to obtain the network quality data between the node a and the node b.

Taking the network quality data obtained by calculating according to the RTT as an example, the network quality level matched with the RTT can be obtained according to the RTT of the network between the node a and the node b and the corresponding relationship between different RTT ranges and network quality levels, so as to obtain the network quality data between the node a and the node b. It should be noted that, in the case that the node a sends multiple TCP packets for one link with the node b, the RTT may specifically be an average value of RTTs.

Taking the example of obtaining the network quality data by calculating according to the packet loss rate and the RTT, the packet loss rate and the RTT can be converted into an index, and the index is used as the network quality data. For example, the network quality data between node a and node b may be equal to RTT +0.3 × RTT × packet loss rate × 100. As another example, the network quality data between node a and node b may be equal to 100/(101-packet loss x 100)²×RTT。

In the embodiment of the application, the network quality data can be calculated by adopting a calculation formula matched with the current network quality calculation strategy, so that the flexibility of the calculation of the network quality data is improved. Based on this, the network quality data calculated according to the detection result may specifically include: determining a calculation formula matched with a calculation strategy based on a current network quality calculation strategy; and calculating to obtain the network quality data by adopting the calculation formula according to the detection result.

For example, assuming that the current network quality calculation policy considers only the packet loss rate factor, the determined calculation formula matching the calculation policy may be, for example, Q ═ 10-Lr × 10, where Q represents the network quality and Lr represents the packet loss rate. It should be noted that, the calculation formula is exemplified by taking the network quality data as the network quality level, the network quality level includes 11 levels from 0 to 10, and the larger the value of the network quality level is, the better the network quality is.

For another example, assuming that the current network quality calculation policy considers a packet loss rate and an RTT, and the packet loss rate and the RTT are the same in weight when calculating the network quality, the determined calculation formula matching the calculation policy may be, for example, Q RTT +0.3 × Lr × 100, where Q represents the network quality, Lr represents the packet loss rate, and RTT represents the round trip delay.

For another example, assuming that the current network quality calculation policy considers a packet loss rate and an RTT, and the weight of the packet loss rate in calculating the network quality is higher than the RTT, the calculation formula matching the calculation policy determined may be, for example, Q RTT +0.4 × Lr × 100, where Q represents the network quality, Lr represents the packet loss rate, and RTT represents the round trip delay.

For another example, assuming that the current network quality calculation policy considers a packet loss rate and an RTT, and the weight of the packet loss rate in calculating the network quality is lower than the RTT, the determined calculation formula matching the calculation policy may be, for example, Q RTT +0.2 × Lr × 100, where Q represents the network quality, Lr represents the packet loss rate, and RTT represents the round trip delay.

Of course, in other embodiments, the calculation policy and the calculation formula matched with the calculation policy may also be in other forms, which is not limited in this application.

In the embodiment of the present application, after the second computer device obtains the network quality data, the network quality data between the primary node and the secondary node may be considered when implementing load balancing among the plurality of secondary nodes. Specifically, the second computer device may select a target previous-level node from the plurality of previous-level nodes according to the network quality data and the load balancing policy.

For example, referring to fig. 1, taking a target node as the primary node 11 as an example, the second computer device may sort the secondary nodes 21 to 2N according to the sequence of network quality from high to low based on the aforementioned network quality data 1 to obtain a secondary node quality rank corresponding to the primary node 11, and further may select the target secondary node for the primary node 11 based on a load balancing policy and the secondary node quality rank. For example, whether a second-level node ranked first is full may be determined according to the quality ranking of the second-level nodes, if not, the first-level node ranked first is selected as a target second-level node of the first-level node 11, if full, it is further determined whether a second-level node ranked second is full, if not, the second-level node ranked second is selected as a target second-level node of the first-level node 11, if full, it is further determined whether a third-level node ranked third is full, … …, and so on until the network quality does not meet the requirement or there is a second-level node that meets the quality requirement and is not full. It should be noted that the load balancing policy is only an example, and other load balancing policies may be adopted in other embodiments, which is not limited in this application.

Or, for example, the selecting a target previous-level node from the plurality of previous-level nodes according to the network quality data and the load balancing policy may specifically include: selecting at least two previous nodes with descending network quality order from the multiple previous nodes according to the network quality data; and selecting a target superior node from the at least two superior nodes according to a load balancing strategy. Compared with the mode of directly selecting the target previous-level node from the plurality of previous-level nodes, the method can reduce the previous-level node information stored for the target node in the second computer device, and is beneficial to saving resources.

In one embodiment, the first at least two superior nodes having network quality greater than or equal to the network quality threshold may be selected from a descending ranking of network quality based on the network quality threshold. Taking the target node as the primary node 11, and the secondary nodes 21 → 22 → … … → 2N in the order of the network quality from high to low, the network quality level of the secondary node 21 is 7, the network quality level of the secondary node 22 is 6, the network quality level of the secondary node 23 is 5, and the network quality of the secondary node 26 is 4 as an example, when the quality level threshold is 5, the at least two previous nodes may be the secondary node 21, the secondary node 22, and the secondary node 23. Based on the method, the second computer equipment can select the target upper-level node back to the source for the target node through the load balancing technology in at least two upper-level nodes between which the network quality meets certain requirements and the target node.

In another embodiment, the top X previous nodes may be selected from the network quality descending order according to a quantity threshold value X, where X is an integer greater than 1. Taking the target node as the primary node 11 and the secondary nodes 21 → 22 → … … → 2N in descending order of network quality, the at least two nodes above may be the

secondary node

21, 22, 23 and 24 when the quantity threshold X is 4. Based on the method, the second computer equipment can select the target upper-level node back to the source for the target node through a load balancing technology in a certain number of upper-level nodes which are ahead of the network quality between the target node and the second computer equipment.

In this embodiment of the application, in the process of load balancing, the network quality rankings of the at least two upper-level nodes may be considered. For example, taking the target node as the primary node 11 and the network quality descending order of at least two secondary nodes as the secondary node 21 → the secondary node 22 → the secondary node 23 as an example, the second computer device first determines whether the secondary node 21 is fully loaded, selects the secondary node 21 as the target secondary node of the primary node 11 if not fully loaded, further determines whether the secondary node 22 is fully loaded if fully loaded, selects the secondary node 22 as the target secondary node of the primary node 11 if not fully loaded, and further determines whether the ordered secondary node 23 is fully loaded if fully loaded. It should be noted that the load balancing policy is only an example, and other load balancing policies may be adopted in other embodiments, which is not limited in this application.

In the embodiment of the application, multiple links may exist between the target node and the previous-level node, which is beneficial to improving the flexibility of the links between the nodes, and in this case, the network quality data may be specifically used to represent the network quality between the target node and the multiple previous-level nodes for each of the multiple links. Based on this, the selecting a target previous-level node from the plurality of previous-level nodes according to the network quality data and the load balancing policy may specifically include: and respectively selecting target upper-level nodes aiming at various links from the plurality of upper-level nodes according to the network quality data and the load balancing strategy.

Referring to fig. 2, taking the target node as the primary node 11 as an example, two types of links may exist between the target node and the secondary node, where one type of link is a link from the primary node 11 to the secondary node 21, the secondary node 22, and the secondary node 23, and the other type of link is a link from the primary node 11 to the secondary node 21 and the secondary node 23. Based on this, the network quality data may include network quality data a, which may be for one type of link, and network quality data b, which may be for another type of link. Assuming that the network quality data a corresponds to the operator 1 and the network quality data b corresponds to the operator 2, the network quality data a may be used to represent the network qualities of the links corresponding to the operator 1 between the primary node 11 and the secondary node 21 and between the secondary node 22 and the secondary node 23, and the network quality data b may be used to represent the network qualities of the links corresponding to the operator 2 between the primary node 11 and the secondary node 21 and between the secondary node 23.

Further, for one of the links, a target previous-level node may be selected from the

secondary nodes

21, 22 and 23 according to the network quality data a and the load balancing policy; for another type of link, a target previous-level node may be selected from the

secondary nodes

21 and 23 according to the network quality data b and the load balancing policy. For a specific way of selecting a target previous node from a plurality of nodes based on a load balancing policy, reference may be made to the foregoing related description, which is not described herein again.

It can be understood that, in practical applications, in addition to considering the network quality and the load condition, other factors such as cost and the like may also be considered when performing load balancing, and the description of the present application is omitted here.

In the embodiment of the application, after the previous target node is determined, the corresponding relationship between the target node and the previous target node may be configured to the DNS server, so that the DNS server can determine the previous target node corresponding to the target node according to the corresponding relationship and indicate the previous target node to the target node when the target node requests a second node that needs to be returned to the source.

Or after determining the target previous node, the target previous node of the target node may be configured to the target node, so that the target node may directly determine the secondary node that needs to be returned to the source according to the configuration.

By the network source returning method provided by the embodiment of the application, the network quality data is obtained, the network quality data is used for representing the network quality between the target node and a plurality of upper-level nodes thereof, the network quality data is obtained by calculating according to the detection result of the network between the target node and the upper-level nodes, selecting a target superior node from the plurality of superior nodes according to the network quality data and the load balancing strategy, so that the target node can return to the target upper-level node, the second computer equipment determines the target upper-level node which is required to return to the source by the target node according to the network quality data between the target node and the upper-level node, when the specific source returning of the target node to which previous-level node is determined, the network quality data between the target node and the previous-level node is considered, so that the previous-level node with better quality can be selected for the node in the source returning process.

Fig. 4 is a schematic flowchart of a network back-source method according to another embodiment of the present disclosure, where an execution subject of the embodiment may be the primary node and/or the secondary node in fig. 1. As shown in fig. 4, the method of this embodiment may include:

step 401, a first node obtains probe information, where the probe information is used to indicate a plurality of second nodes that the first node network needs to target for;

step 402, the first node detects the network between the first node and the second node according to the detection information to obtain a detection result, wherein the detection result is used for calculating network quality data, and the network quality data is used for representing the network quality between a target node and a plurality of upper-level nodes thereof.

Wherein the first node is the target node, and the second node is the previous-level node; that is, the target node may initiate probing to its previous node, for example, the first node may initiate probing to the second node; or, the first node is the previous-level node, and the second node is the target node, that is, the previous-level node of the target node may initiate a probe to the target node, for example, the second-level node may initiate a probe to the first-level node.

In this embodiment of the application, the detection information may include, for example, Internet Protocol (IP) addresses of a plurality of second nodes that the network detection of the first node needs to be performed on. Further, the first node may send a TCP packet to the second node for network probing based on the IP address of the second node. Of course, in other embodiments, the probe information may indicate the plurality of second nodes in other manners, which is not limited in this application.

In this embodiment of the application, the obtaining, by the first node, the probe information may specifically include: the first node generates the detection information according to the node hierarchy relation related to the first node. For example, assuming that the first node is 11 and the second node 21 to the second node 2N are all upper-level nodes of the first node 11, the first node 11 may generate probe information indicating that network probing of the first node requires for the second node 21 to the second node 2N.

Or, the obtaining of the probe information may specifically include: and receiving the detection information sent by other equipment. For example, the other device may be a probe server, that is, the probe information may be generated by the probe server according to the node information, and the specific manner may be as described in detail with reference to the embodiment shown in fig. 5.

For example, the first node may send a probe request message to the probe server, where the probe request message may include an identification of the first node, and further the first node may receive probe information returned by the probe server according to the probe request message. The identifier of the first node may be, for example, a node name of the first node, and certainly, in other embodiments, the identifier of the first node may also be in other forms, which is not limited in this application.

It should be noted that, in consideration of the change of node information caused by the addition, deletion, modification, and the like of nodes in the network, the probe information also needs to be updated accordingly. For example, the first node may obtain the probe information periodically, or the first node may obtain the probe information in a timed manner, for example, updating the probe information every hour. Of course, in other embodiments, the first node may also be triggered to obtain the probe information in other manners, which is not limited in this application.

For example, referring to fig. 2, taking the first node as the primary node 14 as an example, the probe information obtained by the primary node 14 may indicate that the secondary nodes for which network probing of the primary node 14 needs to be performed include the secondary node 21 and the secondary node 23. The primary node 14 may probe for the secondary node 21 and the secondary node 23 in sequence in a round of network probing. For example, first, the primary node 14 may sequentially send 10 TCP packets to the secondary node 21 and receive a response packet returned by the secondary node 21 to implement probing for the secondary node 21 to obtain a probing result for the secondary node 21, and then, the primary node 14 may sequentially send 10 TCP packets to the secondary node 23 and receive a response packet returned by the secondary node to implement probing for the secondary node 23 to obtain a probing result for the secondary node 23.

It should be noted that, as to the specific form of the detection result, reference may be made to the related description of the foregoing embodiments, and details are not repeated herein.

It should be noted that after obtaining the probing information, the first node may perform network probing periodically or periodically, for example, may perform one round of probing every minute.

In this embodiment of the application, for the situation of multiple types of links, the detection information may be specifically used to indicate that, under the multiple types of links, the first node network detects multiple second nodes that need to be addressed respectively. Correspondingly, the first node may perform detection on the networks between the first node and the second node under multiple types of links according to the detection information, so as to obtain a detection result. Based on this, the network quality data is specifically used for characterizing the network quality between the target node and the plurality of upper-level nodes thereof for each of the plurality of types of links.

In the case of multiple classes of links, the probe request message may further include a class identifier for identifying a link class to obtain probe information corresponding to the link class. In the case that the multi-class link corresponds to multiple operators, since the IP addresses may distinguish different operators, the type identifier may specifically be an IP address of the first node under a specific operator.

For example, referring to fig. 2, taking the first node as the primary node 11 as an example, the detection information obtained by the primary node 11 may indicate that the secondary nodes to which network detection of the link lower node 11 needs to be directed include the secondary node 21, the secondary node 22 and the secondary node 23, and the secondary nodes to which network detection of the link lower node 11 needs to be directed include the secondary node 21 and the secondary node 23. In one-round network detection, the primary node 11 may sequentially detect the secondary node 21, the secondary node 22, and the secondary node 23 for one type of link, and sequentially detect the secondary node 21 and the secondary node 23 for another type of link. For example, the primary node 11 may first sequentially send 10 TCP packets to the secondary node 21 through the PU1, and receive a response packet returned by the secondary node 21, so as to implement detection on the secondary node 21 under a link of one class; next, the primary node 11 may sequentially send 10 TCP packets to the secondary node 22 through the PU1, and receive a response packet returned by the secondary node 22, so as to implement detection on the secondary node 22 under a link of one class; then, the primary node 11 may sequentially send 10 TCP packets to the secondary node 23 through the PU1, and receive a response packet returned by the secondary node 23, so as to implement detection on the secondary node 23 under a link of one class; then, the primary node 11 may sequentially send 10 TCP packets to the secondary node 21 through the PU2, and receive a response packet returned by the secondary node 21, so as to implement probing on the secondary node 21 under another link; finally, the primary node 11 may sequentially send 10 TCP packets to the secondary node 23 through the PU2 and receive a response packet returned by the secondary node 23, so as to implement probing for the secondary node 23 under another link.

For another example, referring to fig. 2, taking the first node as the secondary node 22 as an example, the detection information obtained by the secondary node 22 may indicate that the primary node to which the network detection of the one-type link-down secondary node 22 needs to be directed includes the primary node 11 and the primary node 13, and the primary node to which the network detection of the other-type link-down secondary node 22 needs to be directed is the primary node 12. Under one type of link, the secondary node 22 may sequentially probe the primary node 11 and the primary node 13 for one type of link and probe the primary node 12 for another type of link in one round of network probing.

In the embodiment of the application, after the first node obtains the detection result, the first node may calculate the network quality data according to the detection result, and send the network quality data to the load balancing device. It should be noted that, for specific description of calculating the network quality data according to the detection result, reference may be made to the related description of the foregoing embodiments, and details are not described herein again.

Alternatively, after obtaining the detection result, the first node may send the detection result to another device, for example, the quality computing device in fig. 1, so that the other device calculates the network quality data according to the detection result and sends the network quality data to the load balancing device. Based on the detection result, the other device can receive the detection result sent by the first nodes respectively, and obtain the network quality data aiming at the target nodes respectively based on the detection result.

According to the method for returning the source of the network provided by the embodiment of the application, the detection information is obtained and used for indicating the first node to detect the plurality of second nodes which need to be aimed at by the network, the network between the first node and the second nodes is detected according to the detection information to obtain the detection result, and the detection result is used for calculating the network quality data, so that the second computer equipment can determine the target previous-level node which specifically needs to be returned to the source of the target node according to the network quality data between the target node and the previous-level node.

Fig. 5 is a flowchart illustrating a network back-source method according to another embodiment of the present application, where an execution subject of the embodiment may be the first computer device 30 in fig. 1. As shown in fig. 5, the method of this embodiment may include:

step 501, obtaining node information, wherein the node information comprises hierarchical relationship information of a plurality of first nodes and a plurality of second nodes;

step 502, generating detection information for the plurality of first nodes respectively according to the node information, wherein the detection information of a first node is used for indicating a plurality of second nodes to which network detection needs to be directed;

step 503, correspondingly sending the detection information to the plurality of first nodes, so that the first nodes can perform network detection according to the detection information.

In this embodiment of the application, the first computer device may obtain node information from a data management and control system, where the data management and control system may store data information related to nodes, for example, how many primary nodes a network includes, how many secondary nodes the network includes, a specific node hierarchical relationship between the primary nodes and the secondary nodes, a geographic location of the node, a bandwidth of the node, an IP address of the node, and the like. Of course, in other embodiments, the first computer device may also obtain the node information in other manners, which is not limited in this application.

It is understood that node information is usually changed under the influence of addition, deletion, modification and the like of nodes, and in order to enable probe information to be consistent with the node information as much as possible, the first computer device may update the node information at intervals, thereby triggering the update of the probe information.

The first node may be, for example, a first-level node in fig. 1, and the second node may be, for example, a second-level node in fig. 1; alternatively, the first node may be, for example, a secondary node in fig. 1, and the second node may be, for example, a primary node in fig. 1. Based on this, the hierarchical relationship of the nodes represented by the hierarchical relationship information between the plurality of first nodes and the plurality of second nodes may be as shown in fig. 1, for example.

In this embodiment of the application, after obtaining the node information, the first computer device may generate, according to the node information, probe information for each of the plurality of first nodes. For example, the first computer device may determine, according to the hierarchical relationship information, a plurality of second nodes having a hierarchical relationship with each first node, and the plurality of second nodes having a hierarchical relationship with each first node may detect, for each first node, a plurality of second nodes to which the first node needs to be addressed, and generate the detection information of each first node according to the plurality of second nodes having a hierarchical relationship with each first node.

Taking the node hierarchy as shown in fig. 1, and the first node is the first-level node in fig. 1 as an example, the plurality of second nodes to which network probing needs to be directed, indicated by the probing information for the first node, may be the second-level nodes 21 to 2N. Taking the node hierarchy as shown in fig. 1 and the first node is the second-level node in fig. 1 as an example, the plurality of second nodes to which network probing needs to be directed, indicated by the probing information for the first node, may be the first-level node 11 to the first-level node 1M.

Optionally, the node information may further include: attribute values of the plurality of first node-specific attributes and the plurality of second node-specific attributes; the number of the attribute values is multiple, and the multiple attribute values correspond to the multiple types of links. In one embodiment, the specific attributes may include operator attributes. For example, referring to fig. 2, the attribute value of the specific attribute of the primary node 11 may be operator 1 and operator 2, and it may be understood that operator 1 and operator 2 share the primary node 11, and the primary node 11 is a primary node of both operator 1 and operator 2; the attribute value of the specific attribute of the primary node 12 may be operator 3, and it is understood that the primary node 12 is a primary node of operator 3; the attribute value of the specific attribute of the primary node 13 may be operator 1, and it may be understood that the primary node 13 is a primary node of operator 1; the attribute value of a particular attribute of a level one node 14 may be operator 2, it being understood that the level one node 14 is a level one node of operator 2.

In this embodiment of the present application, the specific attribute is used for a link classification, and a source return can be limited among nodes belonging to the same type of link through the link classification, for example, for a content request received by a port of operator 1 of a first-level node, one link among multiple links corresponding to operator 1 (i.e., three links of PU1 to PI1, PU1 to PI3, and PU1 to PI 5) can be selected to forward the content request to the upper-level node.

Based on this, the generating, according to the node information, probe information for each of the plurality of first nodes may specifically include: determining a plurality of second nodes with hierarchical relationships among the first nodes according to the hierarchical relationship information; generating detection information of each first node according to attribute values of specific attributes of each first node and a plurality of second nodes with hierarchical relationships thereof and according to preset detection logic based on the attribute values, wherein the detection information is used for indicating a plurality of second nodes which need to be targeted by a first node network under a plurality of links.

Wherein the attribute value based probing logic may be used to specify a specific manner of link classification probing based on the attribute value of a particular attribute. Illustratively, the detection logic may specifically include the following first and/or second types.

First, the attribute value includes a first node of a first attribute value, and the probe attribute value includes a second node of the first attribute value. Based on this, the first attribute value of the first node + the first attribute value of the second node may correspond to a type of link.

In the case that the specific attribute is an operator attribute, the first detection logic may be understood as a first node of operator X, and detect a second node of operator X, and taking operator X includes operator 1 and operator 2 as an example, as shown in fig. 2, a primary node 11 of operator 1 may be obtained to detect

secondary nodes

21, 22, and 23 of operator 1 (which may correspond to lines from primary node 11 to secondary node 21, secondary node 22, and secondary node 23 through PU1 in fig. 2, respectively) and a primary node 13 of operator 1 may be obtained to detect

secondary nodes

21, 22, and 23 of operator 1 (which may correspond to lines from primary node 13 to secondary node 21, secondary node 22, and secondary node 23 through PU4 in fig. 2, respectively). Similarly, it is also possible to obtain the primary node 11 of the operator 2 to detect the

secondary nodes

21 and 23 of the operator 1 (which may correspond to the connection of the primary node 11 to the

secondary nodes

21 and 23, respectively, via the PU2 in fig. 2), and the primary node 14 of the operator 2 to detect the

secondary nodes

21 and 23 of the operator 2 (which may correspond to the connection of the primary node 14 to the

secondary nodes

21 and 23, respectively, via the PU5 in fig. 2)

The number of the first attribute values may be one or more. The detection between nodes containing the same attribute value can be realized based on the first detection logic.

Second, the attribute value includes a first node of a second attribute value, and the probe attribute value includes a second node of the second attribute value and the target first attribute value. Based on this, the second attribute value of the first node + the second attribute value of the second node and the second attribute value of the first node + the target first attribute value of the second node may correspond to a type of link.

In the case that the specific attribute is an operator attribute, the second detection logic may be understood as a first node of operator Y, a second node of operator X and operator Y, for example, operator X is operator 3 and operator Y is operator 2, as shown in fig. 2, a primary node 12 of operator 3 may detect a secondary node 22 of operator 3 (which may correspond to a connection line from the primary node 12 to the secondary node 22 through PU3 in fig. 2) and a primary node 12 of operator 3 may detect

secondary nodes

21 and 23 of operator 2 (which may correspond to connection lines from the primary node 12 to the secondary node 21 and the secondary node 23 through PU3, respectively, in fig. 2).

The number of the second attribute values may be one or more, and the target first attribute value may be a part or all of the first attribute values. Based on the second detection logic, not only the detection between the nodes containing the same attribute value can be realized, but also the detection between the nodes containing different attribute values can be realized according to the needs.

In this embodiment, in the case that the number of the probe logics is multiple, considering that the attribute value included in a single first node may not relate to all the probe logics, matching of the probe logics may be performed before probe information generation is performed, and probe information may be generated based on the probe logics matched with the first nodes. For example, generating the detection information of each first node according to the attribute value of the specific attribute of each first node and the plurality of second nodes having the hierarchical relationship therebetween and according to a preset detection logic based on the attribute value may specifically include: according to the attribute value of the specific attribute of each first node, determining a target detection logic matched with the attribute value of each first node from the plurality of detection logics; and generating detection information of each first node according to the attribute values of the specific attributes of each first node and a plurality of second nodes with hierarchical relationship thereof and according to target detection logic matched with the attribute values of each first node.

Optionally, after the detection information is generated, the generated detection information may be adjusted based on a detection adjustment policy, so as to improve the flexibility of detection. The adjustment of the probe information may specifically be to empty the probe information for a certain first node, in which case the first node may not need to perform the probe, or delete the probe of a certain first node for a part of the second nodes.

The detection adjustment strategy can be flexibly realized according to requirements. Illustratively, the probing adjustment strategy includes one or more of: the method is used for detecting the need between nodes caching the same type of content, detecting the need between nodes with certain requirements on network quality and other nodes, or detecting the need between nodes with certain requirements on operator cost and other nodes.

For example, assuming that the probe information generated for the first-level node 11 probes the second-

level nodes

21, 22, and 23 for the first-level node 11, and the first-level node 11 is configured to cache the content of type 1, type 2, and type 3, the second-level node 21 is configured to cache the content of type 1, the second-level node 22 is configured to cache the content of type 2, and type 3, and the second-level node 23 is configured to cache the content of type 4, then since the second-

level nodes

21 and 22 and the first-level node 11 cache the content of the same type, and the second-level node 23 does not cache the content of the same type as the first-level node 11, after the probe information is adjusted according to the probe adjustment policy "the probe needs to be performed between nodes for caching the content of the same type", in the updated probe information, the probe information for the first-level node 11 probes the second-

level nodes

21 and 22 for the first-level node 11.

For example, assuming that the detection information generated for the first-level node 11 is the first-level node 11 to detect the second-

level nodes

21, 22, and 23, the detection information generated for the first-level node 12 is the first-level node 12 to detect the second-

level nodes

21, 22, and 23, the first-level node 11 has a certain requirement on the network quality, and the first-level node 12 has no requirement on the network quality, the detection information is adjusted according to a detection adjustment policy of "detection is required between a node having a certain requirement on the network quality and other nodes", and then, in the updated detection information, the detection information for the first-level node 11 is the first-level node 11 to detect the second-

level nodes

21, 22, and 23, and the detection information for the first-level node 12 is empty.

For example, assuming that the probe information generated for the primary node 11 probes the

secondary nodes

21, 22, and 23 for the primary node 11, the probe information generated for the primary node 13 probes the

secondary nodes

21, 22, and 23 for the primary node 13, and the operator cost of the primary node 11 meets a certain requirement, and the operator cost of the primary node 13 does not meet the requirement, after the probe information is adjusted according to the probe adjustment policy that "probing needs to be performed between a node whose operator cost meets a certain requirement and other nodes", in the updated probe information, the probe information for the primary node 11 probes the

secondary nodes

21, 22, and 23 for the primary node 11, and the probe information for the primary node 13 is empty.

In this embodiment of the application, after the probe information is adjusted according to the probe adjustment policy, the probe information may be correspondingly sent to the plurality of first nodes, for example, the probe information for the first-level node 11 may be sent to the first-level node 11, and the probe information for the second-level node 21 may be sent to the second-level node 21, so that the first nodes can perform network probing according to the probe information of the first-level node. Optionally, the first computer device may actively send the probe information to the first node; alternatively, the first computer device may send the probe information to the first node when the first node requests the probe information from the first node, and the specific manner may be described in relation to the embodiment shown in fig. 4, which is not described herein again.

According to the method for returning the source of the network provided by the embodiment of the application, the node information is obtained, the node information comprises the hierarchical relation information of a plurality of first nodes and a plurality of second nodes, the detection information aiming at the plurality of first nodes is generated according to the node information, and the detection information is correspondingly sent to the plurality of first nodes, so that the first nodes can carry out network detection according to the detection information, the first nodes can carry out detection on the network between the first nodes and the second nodes based on the detection information to obtain the detection result, and the detection result can be used for calculating the network quality data, so that the load balancing equipment can determine the target upper-level node which is required to be returned to the source specifically according to the network quality data between the target node and the upper-level node.

Fig. 6 is a schematic structural diagram of a source device of a network according to an embodiment of the present application; referring to fig. 6, the present embodiment provides a back-source device of a network, which may perform the method shown in fig. 3, and specifically, the back-source device of the network may include:

an obtaining module 61, configured to obtain network quality data, where the network quality data is used to characterize network quality between a target node and a plurality of previous-level nodes of the target node, and the network quality data is obtained by calculation according to a detection result of a network between the target node and the previous-level nodes;

and a load balancing module 62, configured to select a target previous-level node from the multiple previous-level nodes according to the network quality data and a load balancing policy, so that the target node can return to the target previous-level node.

Optionally, the load balancing module 62 is specifically configured to select, according to the network quality data, at least two previous nodes in descending order of network quality from the multiple previous nodes; and selecting a target superior node from the at least two superior nodes according to a load balancing strategy.

Optionally, there are multiple types of links between the target node and the previous-level node; the network quality data is specifically used for representing the network quality of each of multiple links between the target node and the multiple previous-level nodes;

the load balancing module 62 is specifically configured to select target previous-stage nodes for each type of link from the multiple previous-stage nodes according to the network quality data and the load balancing policy.

Optionally, the multiple types of links correspond to multiple operators.

Optionally, the obtaining module 61 is specifically configured to determine a calculation formula matched with the calculation policy based on the current network quality calculation policy; and calculating to obtain network quality data by adopting the calculation formula according to the detection result.

Optionally, the apparatus further comprises: and the configuration module is used for configuring the corresponding relation between the target node and the target upper-level node to a domain name system server of the target node, or configuring the target upper-level node to the target node.

Optionally, the network comprises a content distribution network.

Optionally, the target node includes a first-level cache node of the content distribution network; the upper level node comprises a second level cache node of the content distribution network.

The apparatus shown in fig. 6 can perform the method of the embodiment shown in fig. 3, and reference may be made to the related description of the embodiment shown in fig. 3 for a part of this embodiment that is not described in detail. The implementation process and technical effect of the technical solution refer to the description in the embodiment shown in fig. 3, and are not described herein again.

In one possible implementation, the structure of the back-source device of the network shown in fig. 6 may be implemented as a computer device, which may be, for example, a load balancing device. As shown in fig. 7, the computer apparatus may include: a processor 71 and a memory 72. Wherein the memory 72 is used for storing a program for supporting the computer device to execute the back-to-source method of the network provided in the embodiment shown in fig. 3, and the processor 71 is configured for executing the program stored in the memory 72.

The program comprises one or more computer instructions which, when executed by the processor 71, are capable of performing the steps of:

Optionally, the processor 71 is further configured to perform all or part of the steps in the embodiment shown in fig. 3.

The computer device may further include a communication interface 73 for communicating with other devices or a communication network.

Fig. 8 is a schematic structural diagram of a source device of a network according to another embodiment of the present application; referring to fig. 8, the present embodiment provides a back-source device of a network, which may perform the method shown in fig. 4, and specifically, the back-source device of the network may include:

an obtaining module 81, configured to obtain probe information, where the probe information is used to indicate a plurality of second nodes that the first node network needs to target for;

a detection module 82, configured to detect the network between the first node and the second node according to the detection information to obtain a detection result, where the detection result is used to calculate network quality data, and the network quality data is used to characterize network quality between a target node and a plurality of nodes above the target node;

Optionally, the obtaining module 81 is specifically configured to receive probe information sent by another device.

Optionally, the probing information is specifically used to indicate that, under multiple types of links, the first node network probes multiple second nodes that need to be addressed respectively;

the detection module 82 is specifically configured to, according to the detection information, detect networks between the first node and the second node under multiple types of links, respectively, to obtain a detection result;

the network quality data is specifically used for characterizing the network quality of each of multiple links between the target node and the multiple previous-level nodes.

Optionally, the multiple types of links correspond to multiple operators.

Optionally, the apparatus further includes a sending module, configured to calculate the network quality data according to the detection result and send the network quality data to a load balancing device, or send the detection result to another device, so that the other device calculates the network quality data according to the detection result and sends the network quality data to the load balancing device, or send the detection result to the load balancing device, so that the load balancing device calculates the network quality data according to the detection result.

Optionally, the sending module is configured to calculate the network quality data according to the detection result, and specifically includes: determining a calculation formula matched with a calculation strategy based on a current network quality calculation strategy; and calculating to obtain the network quality data by adopting the calculation formula according to the detection result.

The apparatus shown in fig. 8 can perform the method of the embodiment shown in fig. 4, and reference may be made to the related description of the embodiment shown in fig. 4 for a part of this embodiment that is not described in detail. The implementation process and technical effect of the technical solution refer to the description in the embodiment shown in fig. 4, and are not described herein again.

In one possible implementation, the structure of the back-source device of the network shown in fig. 8 may be implemented as a network node, i.e. the first node. As shown in fig. 9, the network node may include: a processor 91 and a memory 92. Wherein the memory 92 is used for storing a program for supporting the network node to execute the back-to-source method of the network provided in the embodiment shown in fig. 4, and the processor 91 is configured for executing the program stored in the memory 92.

The program comprises one or more computer instructions which, when executed by the processor 91, are capable of performing the steps of:

obtaining probe information indicating a plurality of second nodes for which the first node network probes are required;

Optionally, the processor 91 is further configured to perform all or part of the steps in the foregoing embodiment shown in fig. 4.

The network node may further include a communication interface 93 for the network node to communicate with other devices or a communication network.

Fig. 10 is a schematic structural diagram of a source device of a network according to another embodiment of the present application; referring to fig. 10, the present embodiment provides a back-source device of a network, which may perform the method shown in fig. 5, and specifically, the back-source device of the network may include:

an obtaining module 101, configured to obtain node information, where the node information includes hierarchical relationship information of a plurality of first nodes and a plurality of second nodes;

a generating module 102, configured to generate, according to the node information, probe information for each of the plurality of first nodes, where the probe information of a first node is used to indicate a plurality of second nodes to which network probing needs to be directed;

a sending module 103, configured to correspondingly send the probe information to the plurality of first nodes, so that the first nodes can perform network probe according to the probe information.

Optionally, the node information further includes: attribute values of the plurality of first node-specific attributes and the plurality of second node-specific attributes; the number of the attribute values is multiple, and the multiple attribute values correspond to the multiple links;

a generating module 102, configured to determine, according to the hierarchical relationship information, a plurality of second nodes having a hierarchical relationship with each first node; and generating detection information of each first node according to attribute values of specific attributes of each first node and a plurality of second nodes with hierarchical relationships thereof and according to preset detection logic based on the attribute values, wherein the detection information is used for indicating a plurality of second nodes which need to be targeted by the first node network under the multi-class links.

Optionally, the specific attribute includes an operator attribute.

Optionally, the number of the detection logics is multiple, and the generating module 102 is specifically configured to generate, according to the attribute value of the specific attribute of each first node and the multiple second nodes having the hierarchical relationship with the first node, the detection information of each first node according to a preset detection logic based on the attribute value, and specifically includes:

according to the attribute value of the specific attribute of each first node, determining a target detection logic matched with the attribute value of each first node from the plurality of detection logics;

and generating detection information of each first node according to the attribute values of the specific attributes of each first node and a plurality of second nodes with hierarchical relations, and according to target detection logic matched with the attribute values of each first node.

Optionally, the detection logic includes: a first node whose attribute values include a first attribute value, a second node whose attribute values include the first attribute value is probed; and/or, the attribute value comprises a first node of a second attribute value, and the probe attribute value comprises a second node of the second attribute value and a target first attribute value.

Optionally, the apparatus further comprises: and the adjusting module is used for adjusting the generated detection information based on the detection adjusting strategy.

Optionally, the detection adjustment policy includes one or more of the following: the method is used for detecting the need between nodes caching the same type of content, detecting the need between nodes with certain requirements on network quality and other nodes, or detecting the need between nodes with certain requirements on operator cost and other nodes.

The apparatus shown in fig. 10 can perform the method of the embodiment shown in fig. 5, and reference may be made to the related description of the embodiment shown in fig. 5 for a part of this embodiment that is not described in detail. The implementation process and technical effect of the technical solution are described in the embodiment shown in fig. 5, and are not described herein again.

In one possible implementation, the structure of the back-source device of the network shown in fig. 10 may be implemented as a computer device, which may be, for example, a probe server. As shown in fig. 11, the computer apparatus may include: a processor 111 and a memory 112. Wherein the memory 112 is used for storing a program for supporting the computer device to execute the back-to-source method of the network provided in the embodiment shown in fig. 5, and the processor 111 is configured for executing the program stored in the memory 112.

The program comprises one or more computer instructions, wherein the one or more computer instructions, when executed by the processor 111, are capable of performing the steps of:

Optionally, the processor 111 is further configured to perform all or part of the steps in the foregoing embodiment shown in fig. 5.

The computer device may further include a communication interface 113 for the computer device to communicate with other devices or a communication network.

In addition, the present application provides a computer storage medium for storing computer software instructions for a terminal, which includes a program for executing the method for returning to the source of the network in the method embodiment shown in fig. 3.

The embodiment of the present application provides a computer storage medium for storing computer software instructions for a terminal, which includes a program for executing the back-source method of the network in the embodiment of the method shown in fig. 4.

The embodiment of the present application provides a computer storage medium for storing computer software instructions for a terminal, which includes a program for executing the back-source method of the network in the embodiment of the method shown in fig. 5.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. With this understanding in mind, the above-described technical solutions and/or portions thereof that contribute to the prior art may be embodied in the form of a computer program product, which may be embodied on one or more computer-usable storage media having computer-usable program code embodied therein (including but not limited to disk storage, CD-ROM, optical storage, etc.).

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of back-sourcing a network, the method comprising:

2. The method of claim 1, the selecting a target superordinate node from the plurality of superordinate nodes according to the network quality data and a load balancing policy, comprising:

selecting at least two previous nodes with descending network quality order from the multiple previous nodes according to the network quality data;

and selecting a target upper-level node from the at least two upper-level nodes according to a load balancing strategy.

3. The method of claim 1, wherein there are multiple types of links between the target node and the previous level node; the network quality data is specifically used for representing the network quality of each of multiple links between the target node and the multiple previous-level nodes;

the selecting a target previous-level node from the plurality of previous-level nodes according to the network quality data and the load balancing policy includes:

and respectively selecting target upper-level nodes aiming at various links from the plurality of upper-level nodes according to the network quality data and the load balancing strategy.

4. The method of claim 3, the multi-class links corresponding to a plurality of operators.

5. The method of claim 1, the obtaining network quality data, comprising:

determining a calculation formula matched with a calculation strategy based on a current network quality calculation strategy;

and calculating to obtain network quality data by adopting the calculation formula according to the detection result.

6. The method of any of claims 1-5, further comprising, after selecting a target previous level node from the plurality of previous level nodes based on the network quality data and a load balancing policy:

configuring the corresponding relation between the target node and the target upper-level node to a domain name system server of the target node;

or, configuring the target upper-level node to the target node.

7. The method of any of claims 1-5, the network comprising a content distribution network.

8. The method of claim 7, the target node comprising a level one cache node of the content distribution network; the upper level node comprises a second level cache node of the content distribution network.

9. A method of back-sourcing a network, the method comprising:

10. The method of claim 9, the obtaining sounding information, comprising:

and receiving the detection information sent by other equipment.

11. The method according to claim 9, wherein the probing information is specifically used to indicate that, under multiple types of links, the first node network probes multiple second nodes that need to be addressed to respectively;

the detecting the network between the first node and the second node according to the detection information to obtain a detection result includes: according to the detection information, networks between the first node and the second node under the links of multiple types are detected respectively, and detection results are obtained;

12. The method of claim 11, the multi-class links correspond to multiple operators.

13. The method according to any of claims 9-12, after probing the network with the second node according to the probing information and obtaining a probing result, further comprising:

calculating to obtain the network quality data according to the detection result, and sending the network quality data to load balancing equipment;

or sending the detection result to intermediate equipment, so that the intermediate equipment calculates the network quality data according to the detection result and sends the network quality data to load balancing equipment;

or sending the detection result to load balancing equipment, and calculating by the load balancing equipment according to the detection result to obtain the network quality data.

14. The method of claim 13, wherein said calculating the network quality data based on the probe results comprises:

and calculating to obtain the network quality data by adopting the calculation formula according to the detection result.

15. A method of back-sourcing a network, the method comprising:

16. The method of claim 15, the node information further comprising: attribute values of the plurality of first node-specific attributes and the plurality of second node-specific attributes; the number of the attribute values is multiple, and the multiple attribute values correspond to the multiple links;

generating, according to the node information, probe information for each of the plurality of first nodes, including:

determining a plurality of second nodes with hierarchical relationships among the first nodes according to the hierarchical relationship information;

generating detection information of each first node according to attribute values of specific attributes of each first node and a plurality of second nodes with hierarchical relationships thereof and according to preset detection logic based on the attribute values, wherein the detection information is used for indicating a plurality of second nodes which need to be targeted by a first node network under a plurality of links.

17. The method of claim 16, the specific attribute comprising an operator attribute.

18. The method according to claim 17, wherein the number of the probing logics is multiple, and the generating of the probing information of each first node according to the attribute value of the specific attribute of each first node and the plurality of second nodes having the hierarchical relationship with each first node and the preset probing logic based on the attribute value comprises:

19. The method of claim 18, the probing logic comprising:

a first node whose attribute values include a first attribute value, a second node whose attribute values include the first attribute value is probed;

and/or, the attribute value comprises a first node of a second attribute value, and the probe attribute value comprises a second node of the second attribute value and a target first attribute value.

20. The method according to any of claims 15-19, before correspondingly sending the probe information to the plurality of first nodes, further comprising:

and adjusting the generated detection information based on a detection adjustment strategy.

21. The method of claim 20, the probe adjustment strategy comprising one or more of:

the method is used for detecting the need between nodes caching the same type of content, detecting the need between nodes with certain requirements on network quality and other nodes, or detecting the need between nodes with certain requirements on operator cost and other nodes.

22. A back-source device of a network, the device comprising:

23. A back-source device of a network, the device comprising:

an obtaining module, configured to obtain probe information, where the probe information is used to indicate a plurality of second nodes that a network of first nodes needs to target for probing;

24. A back-source device of a network, the device comprising:

25. A computer device, comprising: a memory, a processor; the memory is to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of claims 1 to 8.

26. A network node, comprising: a memory, a processor; the memory is to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of claims 9 to 14.

27. A computer device, comprising: a memory, a processor; the memory is to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of any of claims 15 to 21.