CN113542058B - Data source returning method, server and storage medium - Google Patents

Data source returning method, server and storage medium Download PDF

Info

Publication number
CN113542058B
CN113542058B CN202110711202.7A CN202110711202A CN113542058B CN 113542058 B CN113542058 B CN 113542058B CN 202110711202 A CN202110711202 A CN 202110711202A CN 113542058 B CN113542058 B CN 113542058B
Authority
CN
China
Prior art keywords
node
source
path
original
pull
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110711202.7A
Other languages
Chinese (zh)
Other versions
CN113542058A (en
Inventor
苏小杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wangsu Science and Technology Co Ltd
Original Assignee
Wangsu Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wangsu Science and Technology Co Ltd filed Critical Wangsu Science and Technology Co Ltd
Priority to CN202110711202.7A priority Critical patent/CN113542058B/en
Publication of CN113542058A publication Critical patent/CN113542058A/en
Application granted granted Critical
Publication of CN113542058B publication Critical patent/CN113542058B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0852—Delays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00—Routing or path finding of packets in data switching networks
    • H04L45/12—Shortest path evaluation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H04W28/09—Management thereof
    • H04W28/0958—Management thereof based on metrics or performance parameters
    • H04W28/0967—Quality of Service [QoS] parameters
    • H04W28/0975—Quality of Service [QoS] parameters for reducing delays
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/10—Flow control between communication endpoints
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Quality & Reliability (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The embodiment of the invention relates to the technical field of content distribution networks, and discloses a data source returning method, a server and a storage medium. The method for returning the data to the source comprises the following steps: if the number of the nodes needing to pull the stream of the target resource is detected to be increased, acquiring a candidate source returning path of the newly added node and an original source returning path used by the original node; acquiring a shared branch of a newly-added node pull flow and an original node pull flow from the candidate source returning path and the original source returning path; acquiring a source returning path comprising a shared branch as a target source returning path for pulling a target resource; and issuing the target source returning path to each node needing to pull the target resource so as to enable each node to return the source according to the target source returning path. By adopting the embodiment, the cost of returning the data to the source can be reduced.

Description

Data source returning method, server and storage medium
Technical Field
The embodiment of the invention relates to the technical field of content distribution networks, in particular to a data source returning method, a server and a storage medium.
Background
A Content Delivery Network (CDN) is a layer of intelligent virtual Network based on the existing internet, which is formed by placing node servers at various places in the Network. The CDN can redirect the request of the client to the service node closest to the client according to the network flow, the connection and load condition of each node, the distance from the client to the client, the response time and other comprehensive information in real time, and aims to select the node relatively close to the client to send the content required by the client to the client, relieve the condition of network congestion and improve the response speed of a website. The network data service provider may cache a copy of the data resource on the source station to each CDN edge node, that is, a CDN edge node for delivering the data resource in the CDN, and then process and respond to the received user resource request through each CDN edge node, thereby improving a response speed for the user resource request. The current live broadcast is usually implemented by the CDN, for example, a customer pulls a resource to a source station through a stream pulling edge of the CDN, so as to return to the source.
However, if one client initiates a resource request, and after the source returning path of the client is determined, if the source returning path is being used, other clients also initiate source returning requests for the resource, and currently, respective source returning paths are planned for other clients, that is, when multiple clients initiate access requests for the same resource, multiple source returning paths occur, which causes problems of bandwidth waste and cost increase.
Disclosure of Invention
The embodiment of the invention aims to provide a data source returning method, a server and a storage medium, which can reduce the cost of data source returning.
In order to solve the above technical problem, in a first aspect, an embodiment of the present application provides a method for returning data to a source, including: if the number of the nodes needing to pull the stream of the target resource is detected to be increased, acquiring a candidate source returning path of the newly added node and an original source returning path used by the original node; acquiring a shared branch of a newly-added node pull flow and an original node pull flow from the candidate source returning path and the original source returning path; acquiring a source returning path comprising a shared branch as a target source returning path for pulling a target resource; and issuing the target source returning path to each node which needs to pull the target resource so as to enable each node to return the source according to the target source returning path.
In a second aspect, an embodiment of the present application further provides a server, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of data feed back described above.
In a third aspect, the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method for returning data to a source.
In the embodiment of the present application, if the number of nodes that need to pull a stream to a target resource is increased, a source return path corresponding to each of the newly added nodes is usually generated, for example, a source return path of the newly added node is generated based on a shortest path principle, that is, if the number of nodes that need to pull a stream to a target resource is increased, a plurality of different source return paths exist for the same target resource, and when the number of nodes that need to pull a stream to a target resource is detected to be increased, a candidate source return path of the newly added node and an original source return path of an original node are obtained, a shared branch of the newly added node pull stream and the original node pull stream is obtained from the candidate source return path and the original source return path, where the target source return path includes a shared branch, and since the newly added node and the original node share the shared branch to pull a stream, different nodes can use the same target source return path to obtain a target resource, and meanwhile, since the shared branch is used, the utilization rate of a shared branch is improved, the number of the source return paths is also reduced, and the cost of pulling a stream to the same target resource is reduced; in addition, the number of the nodes which need to pull the stream of the target resource is detected, and when the number of the nodes which need to pull the stream of the target resource is increased, the planning of the target source returning path is triggered, so that the target source returning path can be planned in time, and the bandwidth cost is reduced in time.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings which correspond to and are not to be construed as limiting the embodiments, in which elements having the same reference numeral designations represent like elements throughout, and in which the drawings are not to be construed as limiting in scale unless otherwise specified.
Fig. 1 is a schematic structural diagram of a CDN provided in an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a relationship between a central platform and each component in the CDN according to an embodiment of the present application;
FIG. 3 is a flow chart of a method for returning data to a source provided by an embodiment of the present application;
fig. 4 to fig. 6 are schematic diagrams illustrating the central platform determining a return path and acquiring a candidate return path according to the embodiment of the present application;
fig. 7 is a schematic diagram of a specific implementation of obtaining a shared branch according to an embodiment of the present application;
fig. 8 is a schematic diagram of a specific implementation of determining a pull stream object of a newly added node according to an embodiment of the present application;
fig. 9 to fig. 10 are schematic diagrams of two specific implementations of determining a pull flow object of a newly added node when a determination result indicates that an original node identical to an operator to which the newly added node belongs exists according to the application embodiment;
fig. 11 to 12 are schematic diagrams of two specific implementations of determining a pull flow object of a newly added node when a determination result indicates that there is no original node that is the same as an operator to which the newly added node belongs; .
FIG. 13 is a schematic diagram of another embodiment of the present application for determining a pull stream object of a newly added node;
fig. 14 is a schematic diagram of determining a pull stream object of a newly added node when a bandwidth cost of a candidate back-to-source path is smaller than that of an original back-to-source path according to the embodiment of the present application;
fig. 15 is a schematic diagram of a back-source path where a node that does not need to pull a target resource is deleted according to an embodiment of the present application;
16-20 are diagrams of specific implementations of deleting invalid paths provided by embodiments of the present application;
FIG. 21 is a flow chart of a method of data feed back provided by one embodiment of the present application;
fig. 22 is a block diagram of a server according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present invention, and the embodiments may be mutually incorporated and referred to without contradiction.
The structure of the CDN is generally as shown in fig. 1, and includes a source station corresponding to a target resource, a multiline parent node, a layer of parent nodes, and a stream pulling edge node. The source station is a client source station, and the multi-line father node comprises Internet Data Center (IDC) servers of at least two different operators, for example, IDC servers of 3 operators; the first-level father node is an IDC server of a single operator, and the first-level father node is used for converging requests of the pull flow node, for example, the mobile father node, the telecommunication father node and the network communication father node in fig. 1 all belong to the first-level father node, wherein the mobile father node only has the IDC server of the mobile operator, the telecommunication father node only has the IDC server of the telecommunication operator, and the network communication father node only has the IDC server of the network communication operator.
When a client pulls streaming data, a DNS server allocates a corresponding pull flow edge node for the client, the corresponding pull flow edge node acquires a pull flow request of the client, the pull flow edge node requests data from a layer of father nodes, the layer of father nodes inquires whether the layer of father nodes stores target data of the pull flow requested by the client after acquiring the request, and if the layer of father nodes stores the target data, the target data can be returned to the pull flow edge node; and if the target data is not stored in the multi-line father node, pulling the target data from the source station. Currently, a back source path is planned by adopting a shortest path principle in a CDN, and back source paths of different clients for pulling the same target data are different, for example, a back source path of a client 1 to a URL1 already exists currently, and when a new client 2 and a new client 3 back source the URL1, a new back source path is regenerated based on the shortest path principle, and there are multiple back source paths, which results in an increase in cost.
It is understood that if the cross-operator problem is not involved in practical applications, there may be no multi-line parent node in the CDN. A layer of father nodes may also be default in the CDN, that is, the pull stream edge node performs transit without passing through a layer of father nodes or a multi-line father node.
The method for returning data to the source in the embodiment of the present application may be executed by a central platform, where the central platform may include at least one server, and the central platform may also be a server cluster, where the server cluster may be a small cluster, and may be composed of several servers or dozens of servers, such as 3 servers, or may be a large cluster, such as a server cluster composed of 500 or more servers.
For ease of understanding, the relationship between the central platform and each component in the CDN in the present embodiment is shown in fig. 2. The central platform is connected with each streaming edge node, if the CDN comprises a multi-line father node, the central platform can be further connected with the multi-line father node, and if the CDN comprises a layer of father nodes, the central platform can be further connected with the layer of father node; only the central platform is shown in fig. 2 as being connected to each of the pull stream edge nodes. The flow of the method for returning the data to the source is shown in fig. 3.
Step 101: if the central platform detects that the number of nodes needing to pull the target resource is increased, the candidate source returning path of the newly added nodes and the original source returning path used by the original node are obtained.
Specifically, each streamlining edge node in the CDN is connected to the central platform, and each streamlining edge node may report, to the central platform, communication quality evaluation data between the streamlining edge node and the source station according to a preset time interval, where the preset time interval may be 10s, 1s, or the like, that is, the central platform may receive, in real time, communication quality evaluation data between the streamlining edge node and the source station, which are reported by each streamlining edge node; the communication quality evaluation data may be determined according to the delay information obtained by the ping command, for example, the shorter the data transmission delay is, the higher the communication quality between the pull flow edge node and the source station is. The central platform can also receive the information of the operators to which the pull flow edge nodes belong, wherein the information is reported by the pull flow edge nodes.
In this example, the central platform obtains the communication quality evaluation data between the current streaming edge node and the source station and the information of the operator to which the current node belongs. The central platform can acquire the pull flow request of each node, so that the central platform can monitor the number of nodes needing to pull flow of the target resource, when the central platform detects that the number of the nodes needing to pull flow of the target resource is increased, the central platform can acquire a candidate source return path of the newly increased nodes for pulling flow, and meanwhile, the central platform can acquire an original source return path used by an original node.
When the pull stream edge node misses a Uniform Resource Locator (URL) of the target Resource, the central platform determines whether the pull stream edge node can directly pull data from the source station corresponding to the target Resource. If the communication quality evaluation data reported by the pull stream edge node indicates that the pull stream edge node and the corresponding source station can communicate, determining that the pull stream edge node can return to the source, and if the communication quality evaluation data reported by the pull stream edge node indicates that the pull stream edge node and the corresponding source station cannot communicate, realizing that the pull stream edge node can return to the source through the multi-line father node.
The following describes the process of determining a back source path and acquiring a candidate back source path by the central platform with reference to fig. 4 to 6.
As shown in fig. 4, a telecommunications streamlining edge node a misses a URL of a target resource, which indicates that the telecommunications streamlining edge node needs to perform a streamlining on the target resource, the central platform detects whether the URL currently has a streamlining edge node in a pulled target resource, if no streamlining edge node pulls the target resource, the communication quality between the telecommunications streamlining edge node a and a source station can be obtained, if the communication quality between the telecommunications streamlining edge node a and the source station indicates that the telecommunications streamlining edge node a and the source station can communicate, it may be determined that an object of a telecommunications streamlining edge node to a URL1 streamlining is the source station, the central platform feeds back the source return path to the telecommunications streamlining edge node a, the telecommunications streamlining edge node a returns the source according to the source return path, and the source return path is: telecom pull edge node a-telecom source station.
As shown in fig. 5, when the mobile pull stream edge node a needs to pull stream for the target resource, the central platform detects that the mobile pull stream edge node a is not communicable with the telecommunication source station corresponding to the target resource, and needs to forward through the multi-line parent node, and then the central platform may determine that the return source path is: and the mobile pull stream edge node A, the multi-line parent node B and the telecommunication source station. And the central platform issues the source return path to the mobile stream pulling edge node A for the mobile stream pulling edge node A to return the source according to the source return path.
In fig. 4 and 5, a source return path may be determined by using a path shortest principle, and since only one telecommunication pull flow edge node a in fig. 4 pulls a flow to a target resource URL1 and only one mobile pull flow edge node a in fig. 5 pulls a flow to a target resource URL1, the data source return method in the present application is not required to be used at this time.
If it is detected that the number of nodes that need to pull the target resource is increased, as shown in fig. 6, an edge node C that increases the telecommunication pull flow needs to pull the target resource, the source return path of the original node may be obtained as the original source return path, that is, the original source return path is: telecom pull edge node a-telecom source station. The central platform may be based on candidate fallback paths between the telecom streamlining edge node C and the telecom source station, for example, the candidate fallback paths may be: telecom pull edge node C-telecom source station. It should be noted that the candidate source back path is not deployed on the edge node of the telecom pull stream, and if there are multiple source back paths between the newly added node and the source station, there are multiple source back paths.
Step 102: and the central platform acquires the shared branch of the newly-added node pull flow and the original node pull flow from the candidate source return path and the original source return path.
Specifically, since the candidate source returning path is a source returning path for pulling the flow by the newly added node, and the original source returning path is a source returning path for pulling the flow by the original node, if the original source returning path and the candidate source returning path are used to pull the same target resource at the same time, since two source returning paths are used to return the same target resource, a repeated path exists, unnecessary bandwidth consumption is caused, and bandwidth cost is increased. In this embodiment, a shared branch may be formed by combining the candidate back-source path and the original back-source path, so as to reduce the duplicate path and reduce unnecessary bandwidth consumption.
Step 103: and the central platform acquires a source returning path comprising the shared branch as a target source returning path for pulling the target resource.
The target back-to-source path includes a shared leg, or may also include a path between the newly added node and the shared leg. The target back-source path comprises back-source paths of all nodes needing to pull the target resource.
Step 104: and the central platform issues the target source returning path to each node which needs to pull the target resource, so that each node returns the source according to the target source returning path.
Specifically, the target back-source path is issued to each node that needs to pull the target resource, and each node performs the following processing: and adding a target back-to-source path in the node, and then the node can pull the target resource according to the target back-to-source path.
In the embodiment of the present application, if the number of nodes that need to pull a stream for a target resource is increased, a source return path corresponding to each of the newly added nodes is generally generated, for example, a source return path of the newly added node is generated based on a shortest path principle, that is, if the number of nodes that need to pull a stream for a target resource is increased, a plurality of different source return paths exist for the same target resource, and when the number of nodes that need to pull a stream for a target resource is detected to be increased, a candidate source return path of the newly added node and an original source return path of an original node are obtained, a shared branch of the newly added node pull stream and the original node pull stream is obtained from the candidate source return path and the original source return path, where the target source return path includes a shared branch, and since the newly added node and the original node share the shared branch for pulling a stream, different nodes can use the same target source return path to obtain a target resource, and meanwhile, since the shared branch is used, the utilization rate of a shared branch bandwidth is improved, the number of the source return paths is also reduced, and the cost for pulling a stream for the same target resource is reduced; in addition, the number of the nodes which need to pull the stream of the target resource is detected, and when the number of the nodes which need to pull the stream of the target resource is increased, the planning of the target source returning path is triggered, so that the target source returning path can be planned in time, and the bandwidth cost is reduced in time.
In an embodiment, according to a determination result that whether an operator to which the new node belongs is the same as an operator to which the original node belongs, the schematic diagram of the shared branch is obtained as shown in fig. 7:
step 1021: and the central platform judges whether an original node which is the same as the operator to which the newly added node belongs exists or not, and obtains a judgment result.
Specifically, the central node stores information of an operator to which each node belongs, so that information of the operator to which the newly added node belongs and information of the operator to which the original node belongs can be obtained, whether the information of the operator to which the newly added node belongs is the same as the information of the operator to which the original node belongs is judged, and a judgment result is obtained.
Step 1022: and the central platform determines the pull flow object of the newly added node from the candidate source returning path and the original source returning path according to the judgment result.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs, it indicates that the pull flow of the newly added node can be determined based on the original back-to-source path, and the pull flow object of the newly added node can be obtained from the original back-to-source path. And if the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs does not exist, the newly added node is indicated to carry out pull flow across operators, and the pull flow object of the newly added node can be obtained from the candidate source returning path.
Step 1023: and the central platform acquires the shared branch according to the stream pulling object of the newly added node.
Specifically, after determining the stream pulling object of the newly added node, the central platform may obtain a shared branch shared by the stream pulling object of the newly added node and the stream pulling object of the original node based on the stream pulling object of the newly added node.
In this embodiment, because the operator to which the new node belongs is different from the operator to which the original node belongs, and the new node has a condition of performing pull flow across operators, the operator to which the new node belongs can determine a pull flow object applicable to the new node no matter whether the operator to which the new node belongs is the same as the operator to which the original node belongs or not, and a shared branch is generated, so that the applicable scene range of the data source returning method is expanded.
In an embodiment, when the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs, a schematic diagram of determining the pull flow object of the newly added node is shown in fig. 8:
step 1021: and the central platform judges whether an original node which is the same as the operator to which the newly added node belongs exists or not, and obtains a judgment result. If the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs exists, execute step 10221; if the determined result indicates that there is no original node that is the same as the operator to which the newly added node belongs, step 10223 is performed.
Step 10221: the central platform acquires the original node of the original source return path, wherein the pull stream object is a source station or a transfer node.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs, the original node whose pull stream object in the original source return path is the source station or the original node of the intermediate node is obtained, where the intermediate node may be a layer of parent node and a multi-line parent node. And when the operator to which the newly added node belongs is the same as the operator to which the original node belongs, indicating that the newly added node does not need to carry out stream pulling across operators. And acquiring the original node of which the pull stream object in the original source return path is the source station or the transit node.
Step 10222: and the central platform takes the acquired original node as a stream pulling object of the newly added node.
It should be noted that, since the operator to which the new node belongs is the same as the operator to which the original node belongs, it indicates that the new node does not need to pull the stream across the operators, in order to simplify the step of combining the original source return path and the candidate source return path, and increase the speed of combining, the original node whose stream object in the original source return path is the original node of the source station or the transit node can be obtained, the obtained original node can pull the target resource from the source station or the transit node, and the obtained original node is used as the stream object of the new node, that is, the new node pulls the target resource from the obtained original node, shares the path from the stream object of the new node to the source station, and does not need to modify the original source return path, the combining mode is simple and fast, and the influence on the source return of the original node is small.
Step 10223: the central platform judges whether a multi-line father node exists in an original source returning path or not, wherein the multi-line father node comprises data center servers of at least two different operators. Step 10224 may be performed if there is a multi-line parent node in the original return-to-source path, and step 10225 may be performed if there is no multi-line parent node in the original return-to-source path.
Specifically, if the determination result indicates that the original node identical to the operator to which the newly added node belongs does not exist, it indicates that the newly added node needs to perform flow pulling across operators. And if the target resource is stored in the multi-line father node, the original source returning path passes through the multi-line father node, and the target resource is stored in the multi-line father node. Based on this, in this example, whether the target resource is stored in the multi-line parent node is obtained by determining whether the multi-line parent node exists in the original back-to-source path. If the original source returning path does not have the multi-line father node, the fact that the original source returning path does not pass through the multi-line father node is indicated, and the target resource is not stored in the multi-line father node. Because the operator to which the newly added node belongs is different from the operator to which the original node belongs, the target resource needs to be pulled through the multi-line father node, and the target resource is obtained through executing 10225 by the multi-line father node.
Step 10224: and the central platform determines the stream pulling object of the newly added node as a multi-line father node.
Specifically, the central platform determines that the stream pulling object of the newly added node is a multi-line father node, the newly added node can directly pull the target resource from the multi-line father node, and meanwhile, because the original source returning path comprises the multi-line father node, the original source returning path does not need to be modified, and the speed of combining the original source returning path and the candidate source returning path is improved.
Step 10225: the central platform sets the pull object of the multi-line parent node as the source station and performs step 10226.
Specifically, the original source return path does not include the multi-line parent node, and the newly added node needs to pull the target resource through the multi-line parent node, and the central platform sets the stream pulling object of the multi-line parent node as the source station, that is, the multi-line parent node can pull the target resource data from the source station.
Step 10226: the central platform acquires an original node which takes a pull stream object in an original source return path as a source station as a switching node.
Step 10227: and the central platform switches the stream pulling object of the switching node into a multi-line father node and determines the stream pulling object of the newly added node as the multi-line father node.
Step 10231: and acquiring a path between the stream pulling object of the newly added node in the original source returning path and the source station as a shared branch.
Acquiring a path between the newly added node and the stream pulling object as a newly added stream pulling branch; and generating a target back-source path comprising the shared branch and the newly added pull flow branch.
For convenience of understanding, the following describes, with reference to fig. 9 and fig. 10, a process of determining a pull flow object of a newly added node and acquiring a shared branch if the determination result indicates that there is an original node that is the same as an operator to which the newly added node belongs.
The solid line in fig. 9 is the original source return path used currently, the mobile stream pulling edge node a in the original source return path is the original node, the stream pulling object of the mobile stream pulling edge node a is the multi-line parent node B, the stream pulling object of the multi-line parent node B is the telecom source station, and the obtained original node is the mobile stream pulling edge node a. And the newly added node is a mobile pull stream edge node C, and the mobile pull stream edge node A is used as a pull stream object of the mobile pull stream edge node C. Namely, the shared branch is: a mobile pull edge node A, a multi-line father node B and a telecommunication source station; the newly added flow pulling branch circuit is as follows: moving the pulling edge C — moving the pulling edge a. The target back-source node comprises the shared branch and the newly added pull branch. And the central platform issues the target source returning path to the mobile pull flow edge nodes C and A, and the mobile pull flow edge nodes C and A add the target source returning path. Fig. 9 does not show the connection relationship between the central platform and the mobile stream pulling edge node a, a dotted line between the mobile stream pulling edge node a and the mobile stream pulling edge node C is the newly added stream pulling branch, and a dotted line between the central platform and the mobile stream pulling edge node C represents an interaction path between the central platform and the mobile stream pulling edge node C.
The solid line in fig. 10 is the original source return path currently used, the telecommunication pull flow edge node a in the original source return path is the original node, the pull flow object of the telecommunication pull flow edge node a is the source station, and the obtained original node is the telecommunication pull flow edge node a. The newly added node is a telecommunication pull flow edge node C, and the telecommunication pull flow edge node A is used as a pull flow object of the telecommunication pull flow edge node C. Namely, the shared branch is: telecom pull edge node a-telecom source station; the newly added pull flow branch comprises: telecom pull edge node C — telecom pull edge node a. The target back-source node comprises the shared branch and the newly added pull branch. The central platform sends the target source returning path to the telecom pull flow edge node C, and the telecom pull flow edge node C adds the target source returning path. The connection relationship between the central platform and the telecom pull flow edge node a is not shown in fig. 10, and the dashed line between the telecom pull flow edge node a and the telecom pull flow edge node C is the newly added pull flow branch. The dashed line between the central platform and the telecom pull edge node C represents the interaction path of the central platform and the telecom pull edge node C.
Next, with reference to fig. 11 and fig. 12, a process of determining a pull flow object of a new node and acquiring a shared branch if the determination result indicates that there is no original node that is the same as an operator to which the new node belongs is described.
The solid line in fig. 11 is an original source return path currently used, both the mobile stream pulling edge node a and the mobile stream pulling edge node C in the original source return path are original nodes, a stream pulling object of the mobile stream pulling edge node a is a multi-line parent node B, a stream pulling object of the multi-line parent node B is a telecommunication source station, and the mobile stream pulling edge node a is obtained because the stream pulling object of the mobile stream pulling edge node a is the multi-line parent node B. And if the multi-line father node B exists in the original source returning path, the central platform determines that a flow pulling object of the telecommunication flow pulling edge node D is the multi-line father node B. The sharing branch is as follows: multiline parent node B — the telecom source station; the newly added pull flow branch comprises: telecom pull edge node D-multi-line parent node B. Original source returning branch: and the mobile pull flow edge node C, the mobile pull flow edge node A and the multi-line father node B. The target return path comprises: the system comprises a sharing branch, a newly-added pull branch and an original source returning branch. Similarly, the central platform issues the target return path to each pull stream edge node.
The solid line in fig. 12 is the original back-source path currently used, and the original back-source path: telecom pulling flow edge node C-telecom pulling flow edge node A-telecom source station. The telecommunication pulling flow edge node A and the telecommunication pulling flow edge node C in the original source returning path are both original nodes, the newly added node is a mobile pulling flow edge node D, the operator to which the newly added node belongs is different from the operator to which the original node belongs, whether a multi-line father node B exists in the original source returning path or not is judged, and if the fact that the multi-line father node B does not exist in the original source returning path is determined, the central platform sets a pulling flow object of the multi-line father node B as a telecommunication source station. And because the stream pulling object of the telecommunication stream pulling edge node A is a telecommunication source station, acquiring the telecommunication stream pulling edge node A as a switching node, and switching the stream pulling object of the switching node into a multi-line father node B. The sharing branch is as follows: multiline parent node B — the telecom source station; the newly added flow pulling branch circuit is as follows: mobile Pull edge node D-Multi-line parent node B. The original back source branch is changed into: telecom pull edge node C-telecom pull edge node A-multi-line father node B. The target return path comprises: the system comprises a shared branch, a newly added pull branch and an original source return branch. Similarly, the central platform issues the target back-source path to each pull flow edge node.
In one embodiment, before determining the stream pulling object of the newly added node, a schematic diagram of the bandwidth cost of each of the candidate back-to-source path and the original back-to-source path is obtained, as shown in fig. 13.
Step 102-1: the central platform acquires communication quality data reported by the newly added node and the original node respectively, wherein the communication quality data comprises: bandwidth cost of the current node.
Specifically, the newly added node and the original node may report the communication quality data between the newly added node and the source station to the central platform according to a preset time interval, where the preset time interval may be 10s, 1s, and the like, that is, each stream pulling edge node may report the communication quality data in real time, where the communication quality data may include the bandwidth cost of the current node, and may also include communication quality evaluation data of the node and the source station, where the communication quality evaluation data may be determined according to data delay obtained by a ping command, for example, the shorter the data transmission delay is, the higher the communication quality between the node and the source station is. The communication quality data may further include: information of the operator to which the node belongs.
Step 102-2: and the central platform determines the bandwidth cost of the candidate back-source path and the bandwidth cost of the original back-source path according to the communication quality data.
Specifically, since the central platform stores the bandwidth cost of each streaming edge node, the streaming edge nodes in the candidate source-returning paths and the bandwidth cost of the streaming edge nodes can be obtained, and the bandwidth cost of each streaming edge node in each candidate source-returning path is obtained as the bandwidth cost of the candidate source-returning path.
Step 1021: and the central platform judges whether an original node which is the same as the operator to which the newly added node belongs exists or not, and obtains a judgment result.
This determination process is similar to the determination process in the above example, and will not be described herein again.
Step S21: and if the central platform indicates that the original node which is the same as the operator to which the newly added node belongs exists and the bandwidth cost of the candidate source returning path is less than that of the original source returning path, determining the stream pulling object of the newly added node as a source station or a transit node.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs and the bandwidth cost of the candidate back-to-source path is smaller than that of the original back-to-source path, the pull flow object of the newly added node is determined from the candidate back-to-source path, for example, as shown in fig. 14, the candidate back-to-source path is a mobile pull flow edge node C — a multi-line parent node B — a telecommunication source station, and the original back-to-source path is: and the mobile pull stream edge node A, the multi-line parent node B and the telecommunication source station. The newly added nodes are as follows: and if the bandwidth cost of the candidate back-source path is lower than that of the original back-source path, determining that the pull object of the mobile pull edge node C is the multi-line parent node B.
Step S22: and acquiring an original node of which the stream pulling object in the original source returning path is a source station or a transit node as a switching node, and switching the stream pulling object of the switching node into a newly added node.
For example, as shown in fig. 14, the candidate back-source path is a mobile stream edge node C — a multi-line parent node B — a telecom source station, and the original back-source path is: and the mobile pull stream edge node A, the multi-line parent node B and the telecommunication source station. The newly added nodes are as follows: and if the bandwidth cost of the candidate back-source path is lower than that of the original back-source path, determining that the pull stream object of the mobile pull stream edge node C is the multi-line parent node B. And if the original node in the original source return path with the pull stream object as the multi-line father node B is the mobile pull stream edge node A, taking the mobile pull stream edge node A as a switching node, and switching the pull stream object of the switching node into a new node, namely switching the pull stream object of the mobile pull stream edge node A into the new node. After step S22 is performed, step 10231' is performed.
Step 10231': and the central platform acquires a path between the newly added node and the source station in the candidate back source path as a shared branch.
Acquiring a path between a sharing node and an original node as a new pull flow branch; and generating a target back-source path comprising the shared branch and the newly added pull branch.
Step S23: and if the central platform indicates that the original node which is the same as the operator to which the newly added node belongs exists and the bandwidth cost of the original source returning path is less than that of the candidate source returning path, acquiring the pull stream object in the original source returning path as the original node of the source station or the transit node.
Step S24: and the central platform takes the acquired original node as a stream pulling object of the newly added node.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs and the bandwidth cost of the original back-to-source path is smaller than the candidate back-to-source path, steps S23 and S24 are performed, and steps S23 and S24 are similar to steps 10221 and 10222, and will not be described again here.
Step S25: and if the central platform indicates that the original node which is the same as the operator to which the newly added node belongs does not exist according to the judgment result, judging whether a multi-line father node exists in the original back-source path or not, wherein the multi-line father node comprises data center servers of at least two different operators. Step S26 may be executed if the original back-to-source path has a multi-line parent node, and step S27 may be executed if the original back-to-source path does not have a multi-line parent node.
Step S26: and the central platform determines the stream pulling object of the newly added node as a multi-line father node.
Step S27: the central platform sets the pull stream object of the multi-line parent node as the source station, and executes step S28.
Step S28: the central platform acquires an original node which takes a pull stream object in an original source return path as a source station as a switching node.
Step S29: and the central platform switches the stream pulling object of the switching node into a multi-line father node and determines the stream pulling object of the newly added node as the multi-line father node.
S25 to S29 are similar to steps 10223 and 10227, and will not be described here. After step S29 is performed, step 10231 is performed; step 10231 is performed after step S26 is performed.
Step 10231: and acquiring a path between the stream pulling object of the newly added node in the original source returning path and the source station as a shared branch.
In this embodiment, the bandwidth cost of the candidate source returning path and the bandwidth cost of the original source returning path are obtained, and the shared branch is obtained from the source returning path with low bandwidth cost, so that the bandwidth cost of the shared branch is reduced, and the bandwidth cost of the target source returning path is further reduced.
In one embodiment, when it is detected that the number of nodes that need to pull a target resource is reduced, a back source path of the node that does not need to pull the target resource is deleted, where the flow is as shown in fig. 15:
step 101: if the central platform detects that the number of nodes needing to pull the target resource is increased, the candidate source returning path of the newly added nodes and the original source returning path used by the original node are obtained.
Step 102: and the central platform acquires the shared branch of the newly added node and the original node from the candidate source returning path and the original source returning path.
Step 103: and the central platform acquires a source returning path comprising the shared branch as a target source returning path for pulling the target resource.
Step 104: and the central platform issues the target source returning path to each node which needs to pull the target resource, so that each node returns the source according to the target source returning path.
Step 105: if the central platform detects that the number of nodes needing to pull the target resource is reduced, the reduced pull edge nodes are obtained as invalid nodes and original source returning paths used by the original nodes.
Specifically, when the central platform detects that no client needs to pull the target resource under the node, the node does not need to pull the target resource, that is, it is determined that the number of nodes that need to pull the target resource is reduced, and the reduced pull edge nodes are obtained as invalid nodes. This step 105 is executed after the step 104, and the target back-to-source path generated in the step 103 is taken as the original back-to-source path obtained again in this step.
Step 106: and the central platform acquires the path of the invalid node from the original back-to-source path as an invalid back-to-source branch.
Due to the existence of the invalid node, the invalid node exists in the target back-to-source path being used, and the bandwidth cost is consumed.
Step 107: and the central platform deletes the invalid back source branch from the original back source path to generate a new target back source path.
Step 108: and issuing the new target source returning path to each node needing to pull the target resource so as to enable each node to return the source according to the target source returning path.
It should be noted that, in this embodiment, steps 105 to 108 may be executed before step 101.
The process of deleting the invalid back source branch and generating a new target back source path will be described in detail below with reference to fig. 16 to 20.
The solid line in fig. 16 is the currently acquired original back-source path, which includes the multi-line parent node. The original back source path is: and the mobile pull flow edge node C, the mobile pull flow edge node A, the multi-line father node B and the telecommunication source station. If it is detected that the number of nodes that need to perform pull streaming on the target resource is reduced, the reduced pull streaming edge node is obtained as an invalid node, and in fig. 16, since the mobile pull streaming edge node C does not need to perform pull streaming on the target resource, it is determined that the mobile pull streaming edge node C is an invalid node. And obtaining the path of the invalid node from the original back-to-source path as an invalid back-to-source path, namely: mobile pull edge node C — mobile pull edge node a; and deleting the invalid back-source path from the original back-source path to obtain a new target back-source path, namely the target back-source path is a mobile pull stream edge node A, a multi-line father node B and a telecommunication source station. The target back-source path is sent to each pull stream edge node (only the interaction between the central platform and the mobile pull stream edge node C is shown in fig. 16), and the path of the invalid node is deleted.
The original provenance paths in fig. 17 are: the telecommunication pull flow edge node A-telecommunication source station, the telecommunication pull flow edge node C-telecommunication source station. If it is detected that the number of nodes that need to perform pull streaming on the target resource is reduced, the reduced pull streaming edge nodes are obtained as invalid nodes, and in fig. 17, no client under the telecommunication pull streaming edge node a needs to perform pull streaming on the target resource, so that the telecommunication pull streaming edge node a is determined to be an invalid node. Obtaining the path where the invalid node is located from the original back-to-source path as an invalid back-to-source path, namely: the telecommunication pull flow edge node A, a telecommunication source station, deletes an invalid back source path from an original back source path to obtain a target back source path, wherein the target back source path is as follows: telecom pull edge node C, telecom source station. And sending the target back-source path to a telecommunication pull flow edge node A, and deleting the path of the invalid node.
In fig. 18, the condition that the pull stream object of the invalid node is the multi-line parent node is shown, and as shown in fig. 18, the original back source path is: the method comprises the following steps of mobile stream pulling edge node A, a multi-line father node B, a telecommunication source station, mobile stream pulling edge node C, mobile stream pulling edge node A, a multi-line father node B and a telecommunication source station. If it is detected that the number of nodes that need to perform a pull stream on the target resource is reduced, the reduced pull stream edge node is obtained as an invalid node, and in fig. 18, the client under the mobile pull stream edge node a is disconnected from the mobile pull stream edge node a, and at this time, no client under the mobile pull stream edge node a needs to perform a pull stream on the target resource, so that the mobile pull stream edge node a is determined to be an invalid node. Obtaining the path of the invalid node from the original back-to-source path as an invalid back-to-source path, namely: a mobile pull edge node A, a multi-line father node B, a telecommunication source station, and a mobile pull edge node C, a mobile pull edge node A; after deleting the invalid source return path, the mobile stream pulling edge node C cannot acquire the target resource data, so that the stream pulling object of the mobile stream pulling edge node C is changed into the multi-line father node B to obtain a new target source return path, and the new target source return path is changed into: and a mobile pull stream edge node C, a multi-line father node B and a telecommunication source station. And sending the new target back-to-source path to the pull stream edge node, and deleting the path of the invalid node.
Fig. 19 shows a case where the pull flow object of the reduced pull flow edge node is a multi-line parent node and the operator to which the other node belongs is different from the operator to which the source station belongs, and as shown in fig. 19, the obtained original source return path includes: the method comprises the following steps of moving a pull stream edge node A, a multi-line father node B, a telecommunication source station, a telecommunication pull stream edge node D, a multi-line father node B, a telecommunication source station, a moving pull stream edge node C, a moving pull stream edge node A, a multi-line father node B and a telecommunication source station. If it is detected that the number of nodes that need to perform pull streaming on the target resource is reduced, the reduced pull streaming edge nodes are obtained as invalid nodes, and in fig. 19, no client under the telecom pull streaming edge node D needs to perform pull streaming on the target resource, so that the telecom pull streaming edge node D is determined to be an invalid node. Obtaining the path where the invalid node is located from the original back-to-source path as an invalid back-to-source path, namely: telecom pull edge node D-multi-wire parent node B; after deleting the invalid source returning path, the target resources obtained by the mobile pull stream edge node A and the mobile pull stream edge node C are not influenced, and the invalid source returning path can be directly deleted to obtain a new target source returning path which is as follows: and the mobile pull stream edge node C, the mobile pull stream edge node A, the multi-line father node B and the telecommunication source station. And sending the new target back-to-source path to the pull flow edge node, and deleting the path of the invalid node.
Fig. 20 shows a case where the reduced pull stream object of the pull stream edge node is a multi-line parent node and the operator to which the other node belongs is the same as the operator to which the source station belongs, and as shown in fig. 20, the obtained original back-to-source path is: the mobile stream pulling edge node A, the multi-line father node B, the telecommunication source station, the telecommunication stream pulling edge node D, the multi-line father node B and the telecommunication source station. If it is detected that the number of nodes that need to perform pull streaming on the target resource is reduced, the reduced pull streaming edge node is obtained as an invalid node, and in fig. 20, no client under the mobile pull streaming edge node a needs to perform pull streaming on the target resource, so that the mobile pull streaming edge node a is determined to be an invalid node. Obtaining the path where the invalid node is located from the original back-to-source path as an invalid back-to-source path, namely: a mobile pull edge node A, a multi-line father node B and a telecommunication source station; because the operator to which other nodes belong is the same as the operator to which the source station belongs, and resources do not need to be pulled through the multi-line father node B, the invalid source returning path and the telecom stream pulling edge node D-the multi-line father node B are deleted, and a new target source returning path is obtained as follows: telecom pull edge node D — telecom source station. And sending the new target back-to-source path to the pull stream edge node, and deleting the path of the invalid node.
In this embodiment, it is detected that the number of nodes that need to pull the target resource is reduced, the source return path where the reduced edge node of the pull stream is located is obtained, and the target source return path is changed.
The above embodiments can be mutually combined and cited, for example, the following embodiments are examples after being combined, but not limited thereto; the embodiments can be arbitrarily combined into a new embodiment without contradiction.
In one embodiment, the flow of the method of returning the data to the source is shown in FIG. 21.
Step 102-1: the central platform acquires communication quality data reported by the newly added node and the original node respectively, wherein the communication quality data comprises: bandwidth cost of the current node.
Specifically, the newly added node and the original node may report the communication quality data between the newly added node and the source station to the central platform according to a preset time interval, where the preset time interval may be 10s, 1s, and the like, that is, each stream pulling edge node may report the communication quality data in real time, where the communication quality data may include the bandwidth cost of the current node, and may also include communication quality evaluation data of the node and the source station, where the communication quality evaluation data may be determined according to data delay obtained by a ping command, for example, the shorter the data transmission delay is, the higher the communication quality between the node and the source station is. The communication quality data may further include: information of the operator to which the node belongs.
Step 102-2: and the central platform determines the bandwidth cost of the candidate back-source path and the bandwidth cost of the original back-source path according to the communication quality data.
Specifically, since the central platform stores the bandwidth cost of each pull stream edge node, the pull stream edge nodes in the candidate source return paths and the bandwidth cost of the pull stream edge nodes can be obtained, and the bandwidth cost of each pull stream edge node in each candidate source return path is obtained as the bandwidth cost of the candidate source return path.
Step 1021: and the central platform judges whether an original node which is the same as the operator to which the newly added node belongs exists or not, and obtains a judgment result.
This determination process is similar to the determination process in the above example, and will not be described herein again.
Step S21: and if the central platform indicates that the original node which is the same as the operator to which the newly added node belongs exists and the bandwidth cost of the candidate source returning path is less than that of the original source returning path, determining the stream pulling object of the newly added node as a source station or a transit node.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs and the bandwidth cost of the candidate back-to-source path is smaller than that of the original back-to-source path, the pull flow object of the newly added node is determined from the candidate back-to-source path, for example, as shown in fig. 14, the candidate back-to-source path is a mobile pull flow edge node C — a multi-line parent node B — a telecommunication source station, and the original back-to-source path is: and the mobile pull flow edge node A, the multi-line parent node B and the telecommunication source station. The newly added nodes are as follows: and if the bandwidth cost of the candidate back-source path is lower than that of the original back-source path, determining that the pull object of the mobile pull edge node C is the multi-line parent node B.
Step S22: and acquiring an original node of which the stream pulling object in the original source returning path is a source station or a transit node as a switching node, and switching the stream pulling object of the switching node into a newly added node.
For example, as shown in fig. 14, the candidate back-source path is a mobile pull edge node C-a multi-line parent node B-a telecom source station, and the original back-source path is: and the mobile pull stream edge node A, the multi-line parent node B and the telecommunication source station. The newly added nodes are as follows: and if the bandwidth cost of the candidate back-source path is lower than that of the original back-source path, determining that the pull object of the mobile pull edge node C is the multi-line parent node B. If the original node in the original source return path whose stream pulling object is the multi-line father node B is the mobile stream pulling edge node A, the mobile stream pulling edge node A is used as a switching node, the stream pulling object of the switching node is switched to a new node, that is, the stream pulling object of the mobile stream pulling edge node A is switched to the new node. After step S22 is performed, step 10231' is performed.
Step 10231': and the central platform acquires a path between the newly added node and the source station in the candidate source returning path as a shared branch.
Acquiring a path between a sharing node and an original node as a new pull flow branch; and generating a target back-source path comprising the shared branch and the newly added pull branch.
Step S23: and if the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs exists and the bandwidth cost of the original source returning path is smaller than that of the candidate source returning path, the central platform acquires the original node of which the pull stream object in the original source returning path is the source station or the transfer node.
Step S24: and the central platform takes the acquired original node as a stream pulling object of the newly added node.
Specifically, if the determination result indicates that there is an original node that is the same as the operator to which the newly added node belongs and the bandwidth cost of the original back-to-source path is smaller than the candidate back-to-source path, steps S23 and S24 are performed, and steps S23 and S24 are similar to steps 10221 and 10222, and will not be described again here.
Step S25: and if the central platform indicates that the original node which is the same as the operator to which the newly added node belongs does not exist in the judgment result, judging whether a multi-line father node exists in the original source returning path or not, wherein the multi-line father node comprises data center servers of at least two different operators. Step S26 may be performed if the original back-source path has a multi-line parent node, and step S27 may be performed if the original back-source path does not have a multi-line parent node.
Step S26: and the central platform determines the stream pulling object of the newly added node as a multi-line father node.
Step S27: the central platform sets the pull stream object of the multi-line parent node as the source station, and executes step S28.
Step S28: and the central platform acquires an original node which takes a pull stream object in the original source return path as a source station as a switching node.
Step S29: and the central platform switches the stream pulling object of the switching node into a multi-line father node and determines the stream pulling object of the newly added node as the multi-line father node.
S25 to S29 are similar to steps 10223 and 10227, and will not be described herein. After step S29 is performed, step 10231 is performed; step 10231 is performed after step S26 is performed.
Step 10231: and acquiring a path between the stream pulling object of the newly added node in the original source returning path and the source station as a shared branch.
Step 103: and the central platform acquires a back source path comprising the shared branch as a target back source path for pulling the target resource.
Step 104: and the central platform issues the target source returning path to each node which needs to pull the target resource, so that each node returns the source according to the target source returning path.
Embodiments of the present application also relate to a server, as shown in fig. 22, including at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for returning data to the source.
The memory and the processor are connected by a bus, which may include any number of interconnected buses and bridges, linking together one or more of the various circuits of the processor and the memory. The bus may also link various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And the memory may be used to store data used by the processor in performing operations.
The embodiment of the present application further relates to a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method for returning data to a source.
Those skilled in the art can understand that all or part of the steps in the method of the foregoing embodiments may be implemented by a program to instruct related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.

Claims (11)

1. A method for data feed back, comprising:
if the number of the nodes needing to pull the stream of the target resource is detected to be increased, acquiring a candidate source returning path of the newly added node and an original source returning path used by the original node;
acquiring a shared branch of the newly-added node pull flow and the original node pull flow from the candidate source returning path and the original source returning path;
acquiring a source returning path comprising the shared branch as a target source returning path for pulling the target resource;
and issuing the target source returning path to each node which needs to pull the target resource, so that each node can return the source according to the target source returning path.
2. The method according to claim 1, wherein the obtaining the shared branch of the new node pull flow and the original node pull flow from the candidate back-to-source path and the original back-to-source path comprises:
judging whether an original node which is the same as an operator to which the newly added node belongs exists or not, and obtaining a judgment result;
determining a pull stream object of the newly added node from the candidate source returning path and the original source returning path according to the judgment result;
and acquiring the sharing branch according to the stream pulling object of the newly added node.
3. The method according to claim 2, wherein the determining, according to the determination result, the pull stream object of the newly added node from the candidate back-source path and the original back-source path includes:
if the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs exists, acquiring the original node of which the pull stream object in the original source return path is the source station or the transit node;
and using the obtained original node as a pull stream object of the newly added node.
4. The method according to claim 2, wherein the determining, according to the determination result, the stream pulling object of the new node from the candidate back-to-source path and the original back-to-source path includes:
if the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs does not exist, judging whether a multi-line father node exists in the original source returning path or not, wherein the multi-line father node comprises data center servers of at least two different operators;
if yes, determining the stream pulling object of the newly added node as the multi-line father node;
if the source station does not exist, setting the stream pulling object of the multi-line father node as the source station; acquiring an original node of which the pull stream object in the original source return path is a source station as a switching node; and switching the stream pulling object of the switching node into the multi-line father node, and determining the stream pulling object of the newly added node as the multi-line father node.
5. The method according to any one of claims 2 to 4, wherein the obtaining the shared branch according to the pull stream object of the newly added node comprises:
and acquiring a path between the stream pulling object of the newly added node in the original source returning path and the source station as the shared branch.
6. The method according to claim 2, wherein before determining the stream pulling object of the new node from the candidate back-to-source path and the original back-to-source path according to the determination result, the method further comprises:
acquiring communication quality data reported by the newly added node and the original node respectively, wherein the communication quality data comprises: bandwidth cost of the current node;
determining the bandwidth cost of the candidate back-to-source path and the bandwidth cost of the original back-to-source path according to each communication quality data;
the determining, according to the determination result, the stream pulling object of the newly added node from the candidate source returning path and the original source returning path includes:
and if the judgment result indicates that the original node which is the same as the operator to which the newly added node belongs exists and the bandwidth cost of the candidate source returning path is less than that of the original source returning path, determining that the stream pulling object of the newly added node is a source station or a transit node.
7. The method of claim 6, wherein after determining that the pull object of the newly added node is the source station or the transit node, the method further comprises:
and acquiring an original node of which the stream pulling object in the original source returning path is a source station or a transit node as a switching node, and switching the stream pulling object of the switching node into the newly added node.
8. The method according to claim 7, wherein the obtaining the shared branch according to the pull stream object of the newly added node comprises:
and acquiring a path between the newly added node and the source station in the candidate source returning path as the sharing branch.
9. The method of claim 1, further comprising:
if the number of nodes needing to pull the target resource is reduced, acquiring the reduced pull flow edge nodes as invalid nodes and original source returning paths used by the original nodes;
acquiring a path where the invalid node is located from the original back-to-source path as an invalid back-to-source branch;
deleting the invalid back-source branch from the original back-source path to generate a new target back-source path;
and issuing the new target source returning path to each node which needs to pull the target resource, so that each node returns the source according to the target source returning path.
10. A server, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of data feed back as claimed in any one of claims 1 to 9.
11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of data feed back of any one of claims 1 to 9.
CN202110711202.7A 2021-06-25 2021-06-25 Data source returning method, server and storage medium Active CN113542058B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110711202.7A CN113542058B (en) 2021-06-25 2021-06-25 Data source returning method, server and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110711202.7A CN113542058B (en) 2021-06-25 2021-06-25 Data source returning method, server and storage medium

Publications (2)

Publication Number Publication Date
CN113542058A CN113542058A (en) 2021-10-22
CN113542058B true CN113542058B (en) 2022-12-09

Family

ID=78125844

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110711202.7A Active CN113542058B (en) 2021-06-25 2021-06-25 Data source returning method, server and storage medium

Country Status (1)

Country Link
CN (1) CN113542058B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114006943A (en) * 2022-01-04 2022-02-01 北京金山云网络技术有限公司 Data source returning method, device, equipment and storage medium
CN115277486B (en) * 2022-08-01 2024-05-07 广域铭岛数字科技有限公司 Automatic testing method, device and medium based on industrial Internet
CN115412740B (en) * 2022-08-29 2024-03-01 上海哔哩哔哩科技有限公司 Live broadcast back source scheduling method and device, computing equipment and computer storage medium
CN115842863B (en) * 2023-02-24 2023-06-23 天翼云科技有限公司 Cache node scheduling method, device and medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105897581A (en) * 2015-11-20 2016-08-24 乐视云计算有限公司 Media file back source path determination method and device in CDN network
CN107864228A (en) * 2017-12-22 2018-03-30 网宿科技股份有限公司 Connection method for building up and system in a kind of content distributing network
CN108429682A (en) * 2018-02-26 2018-08-21 湖南科技学院 A kind of optimization method and system of network transmission link
CN109040102A (en) * 2018-08-27 2018-12-18 北京搜狐新动力信息技术有限公司 A kind of live transmission method and system of internet live streaming CDN
CN109412946A (en) * 2018-11-14 2019-03-01 网宿科技股份有限公司 Method, apparatus, server and the readable storage medium storing program for executing of source path are returned in a kind of determination
CN110099081A (en) * 2018-01-30 2019-08-06 阿里巴巴集团控股有限公司 CDN system and its time source method, apparatus
CN112235402A (en) * 2020-10-14 2021-01-15 杭州安恒信息技术股份有限公司 Network source returning method, network source returning system and related device
CN112333290A (en) * 2021-01-05 2021-02-05 腾讯科技（深圳）有限公司 Data access control method, device, storage medium and content distribution network system
CN112671718A (en) * 2020-12-03 2021-04-16 网宿科技股份有限公司 Switching method of return link, server and storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109660578B (en) * 2017-10-11 2022-01-21 阿里巴巴集团控股有限公司 CDN back-to-source processing method, device and system
US10938946B2 (en) * 2019-01-14 2021-03-02 Amdocs Development Limited Handshake of application execution between edge nodes
CN109981765B (en) * 2019-03-18 2023-03-24 北京百度网讯科技有限公司 Method and apparatus for determining access path of content distribution network
US20200380050A1 (en) * 2019-06-03 2020-12-03 Wangsu Science & Technology Co., Ltd. Method for acquiring service data and converged cdn system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105897581A (en) * 2015-11-20 2016-08-24 乐视云计算有限公司 Media file back source path determination method and device in CDN network
CN107864228A (en) * 2017-12-22 2018-03-30 网宿科技股份有限公司 Connection method for building up and system in a kind of content distributing network
CN110099081A (en) * 2018-01-30 2019-08-06 阿里巴巴集团控股有限公司 CDN system and its time source method, apparatus
CN108429682A (en) * 2018-02-26 2018-08-21 湖南科技学院 A kind of optimization method and system of network transmission link
CN109040102A (en) * 2018-08-27 2018-12-18 北京搜狐新动力信息技术有限公司 A kind of live transmission method and system of internet live streaming CDN
CN109412946A (en) * 2018-11-14 2019-03-01 网宿科技股份有限公司 Method, apparatus, server and the readable storage medium storing program for executing of source path are returned in a kind of determination
CN112235402A (en) * 2020-10-14 2021-01-15 杭州安恒信息技术股份有限公司 Network source returning method, network source returning system and related device
CN112671718A (en) * 2020-12-03 2021-04-16 网宿科技股份有限公司 Switching method of return link, server and storage medium
CN112333290A (en) * 2021-01-05 2021-02-05 腾讯科技（深圳）有限公司 Data access control method, device, storage medium and content distribution network system

Also Published As

Publication number Publication date
CN113542058A (en) 2021-10-22

Similar Documents

Publication Publication Date Title
CN113542058B (en) Data source returning method, server and storage medium
CN111918273B (en) Network slice selection method and device
CN106031130B (en) Content distribution network framework with edge proxies
US11343306B2 (en) Method, device and system for downloading data block of resource file
EP3729784B1 (en) Methods and apparatus for delivering content
CN113596863B (en) Method, equipment and medium for determining user plane function and providing information
CN105340244A (en) Dynamic content distribution network selection based on context from transient criteria
CN109218363B (en) Content distribution method, network node, and storage medium
US10986537B2 (en) Method of selecting user plane gateway and device of selecting user plane gateway
EP3979671A1 (en) Inter-area media service switching method, server, system, and storage medium
CN110719273A (en) Method for determining back source node, server and computer readable storage medium
CN105577561A (en) Method and system for realizing load balancing between virtualized network elements, and virtualized network element
CN113300962A (en) Path acquisition method, access method, device and equipment
US20140282788A1 (en) System for controlling video distribution in response to a request on reduced video data traffic and a method therefor
CN109873855A (en) A kind of resource acquiring method and system based on block chain network
CN104010046A (en) Server selecting method and system, recording server and measurement servers
CN109788075B (en) Private network system, data acquisition method and edge server
CN111600929B (en) Transmission line detection method, routing strategy generation method and proxy server
KR101469310B1 (en) Method and system for end-to-end QoS guaranteed content delivery on service overlay network
CN112202833A (en) CDN system, request processing method and scheduling server
CN110247847B (en) Method and device for back source routing between nodes
CN101471838B (en) Method, system and equipment for switching source
CN109831467B (en) Data transmission method, equipment and system
JP2023547880A (en) Network nodes and methods in network nodes for providing backup network functionality
CN109195187B (en) Network slice switching method based on log file of network slice server

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant