WO2018127011A1

WO2018127011A1 - Scheduling method and apparatus for transmission clusters of stream data

Info

Publication number: WO2018127011A1
Application number: PCT/CN2017/120140
Authority: WO
Inventors: 殷宇辉
Original assignee: 北京奇虎科技有限公司
Priority date: 2017-01-03
Filing date: 2017-12-29
Publication date: 2018-07-12
Also published as: CN106686101B; CN106686101A

Abstract

A scheduling method and apparatus for transmission clusters of stream data. The method comprises: pre-storing a configuration relationship between position information of a client and at least one transmission cluster, wherein different transmission clusters belong to different transmission service suppliers; correcting the configuration relationship according to transmission performance data of the transmission clusters of each transmission service supplier; scheduling a corresponding first transmission cluster for a first client according to the corrected configuration relationship; and informing the first client of the scheduled first transmission cluster so as to use the same for transmission of stream data. The embodiments of the present invention implement the correction of the corresponding relationship between the position information and the transmission clusters according to the transmission performance data of each transmission cluster, and solve the problem wherein adjustment of transmission clusters may not be implemented according to factors such as network conditions or operating conditions when the transmission clusters provide steam data transmission service for a client.

Description

Scheduling method and device for transmission cluster of stream data

The application claims the priority of the Chinese patent application filed on January 3, 2017, the Chinese Patent Office, the application number is 201710002819.5, and the invention name is "a scheduling method and device for a streaming data transmission cluster", the entire contents of which are incorporated by reference. In this application.

Technical field

The present invention relates to the field of streaming data storage technologies, and in particular, to a scheduling method for a streaming data transmission cluster, and a scheduling device for a streaming data transmission cluster.

Background technique

Streaming data is data that can be transmitted over the network by means of streaming. Large website systems often rely on the Content Delivery Network (CDN) to transmit streaming data. The content distribution network is added to the existing network. A new layer of network structure allows users to transfer data to or near the nearest node. In the content distribution network, a transmission node is deployed to buffer the stream data and provide services to the user nearby.

With the development of network applications with high quality requirements for streaming data such as live video or remote cameras, it is not possible to rely on a content distribution network provided by one vendor to support large network applications. It is an option to rely on multiple vendors to provide content distribution networks for streaming data.

In the prior art, the stream data transmission needs to select one of the content distribution networks corresponding to a plurality of different operators to provide a stream data transmission server, and when the content distribution network is selected, the content distribution network is allocated to the client according to a fixed configuration relationship. It is not possible to adjust the selected content distribution network according to the network status or operating status when the network provides the streaming data transmission service for the client according to the content inventing network.

Summary of the invention

In view of the above problems, the present invention has been made in order to provide a scheduling method and corresponding apparatus for a streaming data transmission cluster that overcomes the above problems or at least partially solves the above problems.

According to an aspect of the present invention, a scheduling method for a transport cluster of streaming data is provided, including:

Pre-storing the location information of the client and the configuration relationship of the at least one transport cluster, wherein different transport clusters belong to different transport service providers;

Correcting the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider;

Scheduling a corresponding first transmission cluster for the first client according to the modified configuration relationship;

The scheduled first transport cluster is notified to the first client for transmission of the streaming data.

According to another aspect of the present invention, a scheduling apparatus for a transport cluster of streaming data is provided, including:

The relationship pre-stored module is configured to pre-store the location information of the client and the configuration relationship of the at least one transport cluster, where different transport clusters belong to different transport service providers;

a configuration relationship correction module, configured to modify the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider;

a cluster scheduling module, configured to schedule a corresponding first transmission group for the first client according to the modified configuration relationship;

The cluster notification module is configured to notify the first transmission cluster of the schedule to the first client for transmission of the stream data.

According to still another aspect of the present invention, a computer program is provided, comprising computer readable code, when said computer readable code is run on a computing device, causing said computing device to perform said transport cluster of said stream data Scheduling method.

According to still another aspect of the present invention, a computer readable medium is provided, wherein the computer program is stored.

A scheduling method and apparatus for a streaming data transmission cluster according to the present invention may be configured by pre-storing location information of a client and configuration relationship of at least one transport cluster according to transmission performance data of a transport cluster of each transport service provider. The relationship is corrected, and the first transmission cluster corresponding to the first client is scheduled according to the modified configuration relationship, and the scheduled first transmission cluster is notified to the first client for transmission of the stream data, so that the client is scheduled. The configuration relationship of the transport cluster can be adjusted according to the transmission performance data, and the correspondence between the location information and the transport cluster is corrected according to the transmission performance data of each transport cluster, and the problem that the streaming data transmission service cannot be provided according to the transport cluster for the client is solved. Adjust the problem of the transport cluster, such as network conditions or health.

The above description is only an overview of the technical solutions of the present invention, and the above-described and other objects, features and advantages of the present invention can be more clearly understood. Specific embodiments of the invention are set forth below.

DRAWINGS

Various other advantages and benefits will become apparent to those skilled in the art from a The drawings are only for the purpose of illustrating the preferred embodiments and are not to be construed as limiting. Throughout the drawings, the same reference numerals are used to refer to the same parts. In the drawing:

FIG. 1 is a flow chart showing the steps of a scheduling method for a streaming data transmission cluster according to Embodiment 1 of the present invention;

2 is a flow chart showing the steps of a scheduling method for a streaming data transmission cluster according to Embodiment 2 of the present invention;

3 is a flow chart showing the steps of a scheduling method for a streaming data transmission cluster according to Embodiment 3 of the present invention;

4 is a structural block diagram of a scheduling apparatus for a transport cluster of streaming data according to Embodiment 4 of the present invention;

Figure 5 shows a block diagram of a computing device for performing the method according to the invention;

Figure 6 shows a storage unit for holding or carrying program code implementing the method according to the invention.

detailed description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While the embodiments of the present invention have been shown in the drawings, the embodiments Rather, these embodiments are provided so that this disclosure will be more fully understood and the scope of the disclosure will be fully disclosed.

1 is a schematic flowchart of the steps of a method for scheduling a stream of data transmission clusters according to the first embodiment of the present invention, which may include the following steps:

Step 101: Pre-store the configuration information of the location information of the client and the at least one transport cluster.

In this embodiment, the transport cluster refers to a computer network system that is connected to each other through the Internet, and uses the server closest to each user to send music, pictures, videos, applications, and other files to the faster and more reliable. Users, to deliver high-performance, scalable and low-cost web content to users. For example, the Content Delivery Network (CDN).

In this embodiment, different transport clusters belong to different transport service providers, and transport service providers refer to transport network providers that provide transport clusters with service stream data transmission. Specifically, any applicable supplier may be selected, and this embodiment does not limit this.

The transport cluster can be used for the transmission of stream data, wherein the stream data is data that can be transmitted on the network by means of streaming, and the stream data can be transmitted from one node to at least one transport node. A plurality of stream data transmissions can exist simultaneously on one transmission node, and the transmission cluster is composed of multiple transmission nodes. The transit node is a server that can be used to receive, store, and distribute streaming data.

Large-scale streaming data transmission systems often rely on transport clusters to transmit convective data. The transport clusters are created by adding a new layer of network structure to the existing network, so that users can transmit data to or near the nearest node. The required data. In the transport cluster, a transport node is deployed to buffer the stream data and provide services to the user. For example, video live applications or remote camera applications often rely on transport clusters to transmit streaming data.

The location information of the client may be information indicating a location area to which the client belongs or geographically belonged to the network, and may include an address segment corresponding to the network address and/or a geographical area corresponding to the location, where the network address (Network) Address) is the logical address that a node on the Internet has in the network. For example, the IP address (English: Internet Protocol Address, also translated as Internet Protocol address). The location information is location information obtained by the client by using the location service. For example, the client invokes geographic location information obtained by Global Positioning System.

In this embodiment, the server may pre-store the configuration relationship between the location information of the client and the at least one transport cluster, where the configuration relationship is a correspondence between the location information and the at least one transport cluster, and is used according to the location information of the client. The client allocates a corresponding transport cluster to provide a streaming data transfer service. For example, the configuration relationship may be a correspondence between a network address segment and at least one transport cluster, or a correspondence between a geographic region and at least one transport cluster.

The pre-stored configuration relationship may be any applicable configuration relationship that is manually set, or may be configured to analyze the configuration relationship of each transport cluster for different location areas according to historical data, and may be any applicable configuration relationship. This is not a limitation.

Specifically, there may be multiple transmission clusters corresponding to one location information, and multiple transmission clusters may be recorded. The prior ranking indicates that the transmission performance is better, and may be used as the preferred transmission cluster.

Step 102: Correct the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider.

The transmission performance data is performance data when the client and the transmission cluster perform streaming data transmission, and specifically includes a code rate, a frame rate, and the like when the stream data is transmitted. The transmission performance data of the transmission cluster may be data collected by at least one client during the stream data transmission, and the transmission performance data of each transmission cluster obtained by synthesizing the data reported by the plurality of clients.

In this embodiment, the transmission performance data of the transmission cluster of each transmission service provider is obtained by each client periodically, for example, the code rate when the client periodically reports the stream data transmission, and the client user selection or client. The frame rate of the video stream data that is switched according to the network status.

According to the location information carried by each client when transmitting the transmission performance data, the transmission performance data corresponding to each location information of each transmission cluster is determined. Since the same transmission cluster is for different geographical regions, that is, for different location information, the transmission performance data may be Differently, as time changes, the transmission performance data of each transmission cluster corresponding to each location information also changes. The configuration relationship is corrected according to the transmission performance data of each transmission cluster.

Specifically, the modified configuration relationship may be a transmission cluster corresponding to one location information, modified to a transmission cluster with the best transmission performance data, or reordered each transmission cluster according to the transmission performance data, and the sorted transmission cluster. The order corrects the configuration relationship.

Step 103: Schedule a corresponding first transport cluster for the first client according to the modified configuration relationship.

In this embodiment, the first client requests to allocate a transport cluster for the stream data transmission, and the server searches for the corresponding first transport cluster according to the location information of the first client according to the modified configuration relationship. Specifically, the first client sends the location information to the server responsible for scheduling the transmission cluster, and the server responsible for scheduling the transmission cluster searches for the transmission cluster corresponding to the location relationship of the first client according to the locally stored configuration relationship, and finds the The transport cluster is the first transport cluster. For example, the location information corresponding to the location information of the first client is Beijing Unicom, and the transport cluster corresponding to Beijing Unicom is searched, that is, the transport cluster corresponding to the location information, and the transport cluster corresponding to Beijing Unicom is found as the first transport cluster.

Step 104: Notify the scheduled first transmission cluster to the first client for transmission of the stream data.

In this embodiment, the server notifies the first transmission cluster that is scheduled according to the configuration relationship to the first client, and the first client establishes a connection with the first transport cluster to complete the transmission of the stream data. Specifically, the identifier of the first transmission cluster or the domain name address is notified to the first client, where the first client sends a stream data transmission request to the first transmission cluster according to the identifier or the domain name address, and the first transmission cluster can feed back a transmission cluster. The transit node in the first client, the first client establishes a connection transport stream data with the transit node.

In summary, according to the embodiment of the present invention, the configuration relationship is corrected according to the transmission performance data of the transmission cluster of each transmission service provider by pre-storing the location information of the client and the configuration relationship of the at least one transmission cluster, according to the correction. The configuration relationship is that the first transmission cluster corresponding to the first client is scheduled, and the scheduled first transmission cluster is notified to the first client for transmission of the streaming data, so that the configuration relationship of the transmission cluster is scheduled for the client. According to the transmission performance data, the correspondence between the location information and the transmission cluster is corrected according to the transmission performance data of each transmission cluster, and the network status or running status when the streaming data transmission service cannot be provided according to the transmission cluster for the client is solved. Adjust the problem of the transport cluster.

In the embodiment of the present invention, preferably, the transmission performance data carries a client identifier and a transmission cluster identifier corresponding to a transmission process, and the configuration relationship is performed according to transmission performance data of a transmission cluster of each transmission service provider. One implementation manner of correcting is: collecting transmission performance data of multiple clients corresponding to the same location information to the same transmission cluster, and calculating an average value; by comparing whether the average value reaches a set threshold, or by comparing the same location The information corresponds to the average value of different transmission clusters, and the configuration relationship between the location information and the transmission cluster is corrected.

The client identifier refers to the identifier of the client that uploads the transmission performance data, and the transport cluster identifier refers to the identifier of the transport cluster to which the client that transmits the transmission performance data is connected.

Each client periodically reports the transmission performance data, and the reported transmission performance data carries the client identifier and the transmission cluster identifier of the transmission process corresponding to the transmission performance data, and reports the location information of the client in the corresponding transmission process. According to the location information reported by the client, the transmission performance data of multiple clients corresponding to the same location information to the same transmission cluster is found, and the average value of the transmission performance data is calculated, and multiple clients corresponding to each location information are obtained in this manner. The transmission performance data of each transmission cluster is collected and the average value is calculated separately.

Correcting the configuration relationship between the location information and the transmission cluster, whether the average value is compared with the set threshold, and if the average value is set, the configuration relationship may be updated by the corresponding relationship between the transmission cluster and the location information; or The configuration relationship between the location information and each transport cluster can be updated by comparing the average values of different transport clusters corresponding to the same location information according to the ranking of the average values.

In the embodiment of the present invention, preferably, the configuration relationship is a correspondence between a location area where the client is located and a transmission cluster, and the modified configuration relationship is one of the first transmission clusters corresponding to the first client scheduling. The implementation is as follows: extracting the network address and/or the location information of the first client; identifying the location area to which the first client belongs according to the network address and/or the location information; and searching for the location relationship according to the configuration relationship The first transport cluster of the identified location area configuration.

The configuration relationship is a correspondence between the location area of the client and the transport cluster, and at least one of the network address and the location information of the first client is extracted, and at least one of the network address and the location information is used to identify the location where the first client is located. The location area searches for the transport cluster corresponding to the identified location area according to the modified configuration relationship, and the discovered transport cluster is the first transport cluster. The network address and the location information may be reported by the client when requesting to schedule the transmission cluster.

Referring to FIG. 2, a schematic flowchart of a step of a method for scheduling a stream of a data transmission cluster according to a second embodiment of the present invention is shown.

Step 201: Pre-store the configuration relationship between the location information of the client and the at least one transport cluster.

In the embodiment, the specific manner is the same as the description of other embodiments, and details are not described herein.

Step 202: Collect transmission performance data reported by multiple clients when performing streaming data transmission with each transport cluster.

The transmission performance data includes at least one of a code rate and a frame rate. The client can report the transmission performance data when the stream data is transmitted. The transmission performance data may be reported according to the request of the server, or the transmission performance data may be reported periodically. When the client performs streaming data transmission with each transport cluster, the transmission performance data is reported separately, and the server collects the transmission performance data reported by each client.

Step 203: Correct the configuration relationship according to the transmission performance data of the transmission cluster of each transmission service provider.

Step 204: Receive a scheduling request of the first client to allocate a transport cluster.

In this embodiment, the first client needs to transmit the stream data, and sends a scheduling request for allocating the transport cluster to the server, and the server receives the scheduling request sent by the first client. The server is a cluster scheduling server, which is used to schedule the server for transmitting the cluster for the client.

Step 205: Search for multiple transport clusters corresponding to the first client according to the modified configuration relationship.

In this embodiment, the configuration relationship between the location information and the transport cluster may be that one location information corresponds to multiple transport clusters, and according to the modified configuration relationship, the transport cluster corresponding to the location information of the first client is searched, and the transport cluster is found. For multiple transport clusters.

Step 206: Select a first transmission cluster that meets the setting condition from the plurality of transmission clusters.

In this embodiment, a transmission cluster that satisfies the setting condition is selected from a plurality of transmission clusters, wherein the setting condition may include that the number of historical selections is lower than a set ratio, the ranking is after the historically selected transmission cluster, and is greater than a setting. Priority or transmission performance meets the set requirements.

Specifically, according to a setting condition, a transmission cluster whose number of historical selections is lower than a set ratio is selected from a plurality of transmission clusters, for example, a selected ratio may be set for each transmission cluster in advance, if the transmission cluster is selected in history. If the number of times selected in the record is lower than the set ratio, the transmission cluster is selected. The set ratio can be any applicable ratio, which is not limited in this embodiment. According to another setting condition, from the plurality of transmission clusters, according to the historically selected transmission cluster, the transmission cluster that has not been selected recently is selected. For example, if three of the four transmission clusters have just been selected, the selection is performed. Unselected transport cluster. According to another setting condition, priority is set for multiple transmission clusters, and a transmission cluster larger than the set priority is selected. The transmission clusters whose transmission performance meets the setting requirements are selected from the plurality of transmission clusters, for example, the transmission clusters larger than the set threshold are selected according to the transmission performance data. Specifically, it may be any applicable setting requirement, and this embodiment does not limit this.

Step 207: When the scheduling request indicates that the streaming data is uploaded, the flow identifier is allocated to the streaming data to be uploaded.

In this embodiment, the flow identifier refers to an identifier that is allocated to each stream data to distinguish the stream data. For example, the server or the server that schedules the transport cluster may assign an identifier to the stream data to be uploaded. The scheduling request is identified, and the transmission cluster is allocated for the transmission of the stream data according to the scheduling request, and the allocation result is fed back to the sender of the scheduling request, and the server is instructed to upload the stream data, and the server may further allocate a stream identifier for the stream data to be uploaded.

Step 208: Combine the flow identifier with the domain name of the scheduled transport cluster into a streaming address notification to the first client, so that the client performs the transmission of the streaming data according to the streaming address.

In this embodiment, the streaming address is an address to be accessed when the client performs streaming data transmission, parsing the streaming address, initiating a handshake, establishing a connection of the streaming data transmission, and then initiating a transmission request, and the server responding to the transmission request, the client The code for streaming data transmission is obtained, the client parses the code of the stream data transmission, and executes the code of the stream data transmission to start the transmission of the stream data.

The server that schedules the transmission cluster allocates a flow identifier and a first transport cluster for the flow data according to the scheduling request, and combines the flow identifier and the domain name of the first transport cluster into a streaming address, and sends the streaming address to the first client, The client transmits the stream data according to the streaming address.

In this embodiment, preferably, the scheduling request carries a protocol type of the first client, and the implementation manner of combining the flow identifier with a domain name of a scheduled transmission cluster into a streaming address is: The protocol type is a protocol header, and the flow identifier is combined with the domain name of the scheduled transport cluster into a streaming address.

The protocol type of the first client refers to the protocol type of the stream data transmission supported and selected by the first client. For example, the RTMP full name Routing Table Maintenance Protocol is in the AppleTalk protocol group, and the routing table maintenance protocol ( RTMP (Routing Table Protocol) is a transport layer protocol that establishes and maintains a routing table in an AppleTalk router. RTMP is based on the Routing Information Protocol (RIP). Like RIP, RTMP uses hop count as the routing metric. The number of hops that the number of routers or other intermediate media nodes that must pass through a packet is sent from the source network to the destination network.

In this embodiment, the protocol identifier of the first client is a protocol header of the transport address, and the domain identifier is combined with the domain name of the scheduled transport cluster into a streaming address.

Step 209: Receive target stream data uploaded by the first client, and push the target stream data to a storage server that stores stream data of multiple transport clusters.

In this embodiment, the target stream data is stream data uploaded by the first client to the transport cluster. The target stream data is received, and the target stream data is pushed to a server that stores the stream data, and specifically may be a storage server dedicated to storing stream data of a plurality of transport clusters.

Step 210: Receive a scheduling request that the second client acquires the target stream data, and notify the first transmission cluster that stores the target stream data to the second client.

In this embodiment, the scheduling request of the second client is received, and the scheduling request is a scheduling request for acquiring the target stream data, and the first transmission cluster storing the target stream data is notified to the second client according to the scheduling request of the second client. Specifically, the address of the transmission node having the target stream data in the first transmission cluster may be notified to the second client.

Step 211: Receive a scheduling request that the second client replaces the first transport cluster, and schedule a second transport cluster for the second client according to the configuration relationship, where the second transport cluster retrieves the Target stream data.

In this embodiment, the second client sends a scheduling request to replace the first transmission cluster, for example, because the transmission speed between the second client and the first transmission cluster cannot meet the requirement of video live broadcast. Receiving a scheduling request for replacing the first transport cluster, scheduling a transport cluster for the second client according to the configuration relationship between the location information of the second client and the transport cluster, and scheduling the transport cluster as the second transport cluster. The second transport cluster establishes a connection with the storage server storing the target stream data, and transmits the target stream data to the second transport cluster.

In summary, according to the embodiment of the present invention, the transmission performance data reported by multiple clients when performing streaming data transmission with each transport cluster is collected by pre-storing the location information of the client and the configuration relationship of the at least one transport cluster, according to each transmission. The transmission performance data of the service provider's transmission cluster is modified, so that the configuration relationship of the transmission cluster for the client can be adjusted according to the transmission performance data reported by each client, and the transmission according to each transmission cluster is realized. The performance data, the relationship between the location information and the transport cluster is corrected, and the problem that the transport cluster cannot be adjusted according to the network status or the running status when the transport cluster provides the streaming data transmission service to the client is solved.

Further, by receiving the scheduling request of the first client to allocate the transmission cluster, searching for the plurality of transmission clusters corresponding to the first client according to the modified configuration relationship, and selecting from the plurality of transmission clusters that the setting conditions are met The first transmission cluster enables a client to allocate a transport cluster according to certain conditions when multiple transport clusters are selected according to the configuration relationship, so as to fully utilize each transport cluster.

Further, when the scheduling request is instructed to upload the stream data, the stream identifier is allocated to the stream data to be uploaded, and the domain identifier and the domain name of the scheduled transport cluster are combined into a stream transmission address notification to the first client for The client performs the transmission of the streaming data according to the streaming address, so that the server that schedules the transport cluster for the client may also generate a streaming address for the streaming data, so that the client accesses the address to complete the streaming data transmission.

Further, receiving the target stream data uploaded by the first client, pushing the target stream data to a storage server storing stream data of the plurality of transport clusters, and receiving a scheduling request of the second client to acquire the target stream data, and Notifying the first transmission cluster storing the target stream data to the second client, so that the stream data can be saved to the storage server, and the storage server is an intermediate service for streaming data transmission across the transport cluster, and realizing the transmission of the stream data across the transport cluster .

Referring to FIG. 3, a schematic flowchart of a step of a method for scheduling a stream of a data transmission cluster according to a third embodiment of the present invention is shown.

Step 301: Pre-store the configuration relationship between the location information of the client and the at least one transport cluster.

Step 302: Correct the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider.

In step 303, the first client determines that there is a new transmission cluster.

At least one transport cluster provides a streaming data transmission service for the first client. When the new transport cluster provides a streaming data transmission service for the client, the first client determines that there is a new transport cluster, and the specific manner may be any applicable manner. This embodiment does not limit this. For example, the first client may obtain the first cluster list that records all the transport clusters from the cluster management server, and determine that there is a new transport cluster by comparing the first cluster list with the locally stored second cluster list; or the first client The terminal can determine that there is a new transport cluster by receiving a new transport cluster notification sent by the cluster management server. In the present invention, the cluster management server is a server for managing a transport cluster.

In this embodiment, preferably, the first client determines that there is a newly added transport cluster: the first client obtains, from the cluster management server, a first cluster list that records all transport clusters; The first client determines that there is a new transport cluster by comparing the first cluster list with the locally stored second cluster list.

The cluster management server is the server that manages the transport cluster. The first cluster list is a list of transport clusters that are currently providing streaming data transport services on the cluster management server. The second cluster list is a list of transport clusters that provide streaming data transport services local to the first client. The first client downloads from the cluster management server to the local device, and then compares the first cluster list and the second cluster list. If the first cluster list has an identifier of the transport cluster that is not in the second cluster list, it is determined that there is a new transmission. Cluster.

In this embodiment, preferably, the method further includes: if the first client determines that there is a target transmission cluster that has been deleted, by comparing the first cluster list with the locally stored second cluster list, Then delete the communication configuration code corresponding to the locally saved target transmission cluster.

The target transport cluster is a transport cluster that no longer serves streaming data transfers. The first client compares the first cluster list with the second cluster list. If the second cluster list has an identifier of the transport cluster that is not in the first cluster list, it is determined that there is a deleted target transport cluster. The communication configuration code corresponding to the target transmission cluster saved locally by the first client is deleted.

In this embodiment, preferably, the method further includes: the first client updating the second cluster list by using the first cluster list of the cluster management server.

The first client downloads the first cluster list from the cluster management server, compares the first cluster list and the second cluster list, and updates the second cluster list with the first cluster list, specifically deleting the second cluster list, and the first The cluster list is saved locally as a new second cluster list, or the newly added content in the first cluster list is added to the local second cluster list, or the content deleted in the first cluster list is removed from the local second cluster. Remove from the list.

Step 304: The first client downloads a corresponding communication configuration code from the communication configuration code base.

In this embodiment, the communication configuration code is code that can be embedded and configured to configure communication between the client and the transport cluster, and the execution communication configuration code can be used to encapsulate the scheduling request and parse the scheduling result. When different transmission clusters perform transmission node scheduling, the methods of encapsulating scheduling requests and parsing scheduling results are different, and corresponding communication configuration codes are required. For example, the communication configuration code can be script code written in the Lua programming language, and the application uses the Lua language as an embedded scripting language to achieve configurability and scalability.

The communication configuration code library is a database in which the communication configuration code corresponding to each transmission cluster is stored, and the communication configuration code library can be used on any applicable server, which is not limited in this embodiment. For example, it can be on a cluster management server.

After determining that the new transmission cluster exists, the first client finds the communication configuration code corresponding to the newly added transmission cluster from the communication configuration code base, and downloads the communication configuration code corresponding to the newly added transmission cluster to the local.

Step 305: Schedule a corresponding first transport cluster for the first client according to the modified configuration relationship.

Step 306, notifying the scheduled first transmission cluster to the first client for transmission of the stream data.

Step 307, when the newly added transport cluster is invoked, the first client interprets and executes the communication configuration code by using a preset interpreter, and the communication configuration code performs the transmission node according to the communication protocol of the newly added transport cluster. The encapsulation of the scheduling request.

In this embodiment, the newly added transport cluster is the first transport cluster. The first client calls the newly added transport cluster, which means that the first client transmits the data through the newly added transport cluster. Specifically, the first client actively selects the newly added transport cluster, or the first client receives the cluster schedule. Select a new transport cluster for the client based on the request of the first client.

The interpreter (English: Interpreter), also translated as an interpreter, is a computer program that translates high-level programming languages directly and line by line. The interpreter does not translate the entire program at once, just like a "middleman", each time you run the program, you must first switch to another language and run it. It runs immediately after translating a line of program descriptions, then translates the next line, and then runs, so it keeps going.

There are different interpreters for different programming languages. In the present embodiment, the preset interpreter is an interpreter that can interpret and execute the communication configuration code. For example, the communication configuration code is written based on the Lua programming language, and the preset interpreter is a general interpreter for the Lua language.

The communication protocol of the newly added transport cluster refers to the rules and conventions that the client must follow to complete communication or service with the transport cluster. For example, the encapsulation rule that the client sends a scheduling request to the transport cluster, the network address of the scheduling server that the client sends the scheduling request to the transport cluster, and the parsing rules after the client receives the scheduling result.

The first client interprets and executes the communication configuration code by using a preset interpreter to encapsulate the scheduling request, wherein the scheduling request is a scheduling request of the transmitting node sent by the client to the transmission cluster. For example, the Lua language universal interpreter is used to interpret and execute the communication configuration code corresponding to the transmission cluster, and the communication configuration code is executed to implement encapsulation of the IP scheduling request data packet to be sent by the client. Specifically, the content included in the data transmission request packet of different transmission clusters is different. Some transmission clusters agree that the IP scheduling request data packet is the identifier of the stream data and the specific string after directly transmitting the domain name address of the cluster, and some The transport cluster contract IP scheduling request packet is a domain name address of the transport cluster in a custom format, an identifier of the stream data, and a specific string.

Step 308: The first client sends the encapsulated scheduling request to the newly added transport cluster.

In this embodiment, the first client sends the encapsulated scheduling request to the newly added transport cluster, and may specifically send the encapsulated scheduling request when accessing the network address recorded by the communication configuration code corresponding to the transport cluster. For example, the network address may be a domain name push stream address of the transport cluster in the live broadcast application, and the domain name push stream address may be parsed to send the encapsulated scheduling request to the server for selecting the transport node in the transport cluster.

In this embodiment, preferably, the communication configuration code further records a network address of the newly added transmission cluster, and the first client sends an encapsulated scheduling request to an implementation of the newly added transmission cluster. The method is: the first client sends the encapsulated scheduling request to the newly added transport cluster according to the network address of the newly added transport cluster indicated by the communication configuration code.

The network address of the newly added transport cluster is the domain name address of the calling transport cluster. The first client resolves the network address and accesses the encapsulated scheduling request to the transport cluster corresponding to the network address. Specifically analyzing the network address of the newly added transport cluster indicated by the communication configuration code may obtain the address of the server for scheduling the transport node, and then send the encapsulated scheduling request to the server.

Step 309: The first client performs stream data transmission according to the transmission node scheduled by the newly added transmission cluster.

In this embodiment, the newly added transmission cluster is the first client scheduling transmission node, and specifically, the scheduling is performed according to at least one type of information such as the network address of the first client and the geographical location of the first client, and the selected transmission node is the first The transit node with a good network connection of the client may specifically allocate the transit node for the first client according to any applicable scheduling logic, which is not limited in this embodiment. The first client establishes a connection with the scheduled transit node to perform the transmission of the stream data, and specifically includes the first client uploading or downloading the stream data.

In this embodiment, preferably, the first client performs the transmission of the stream data according to the transmission node scheduled by the newly added transmission cluster: the first client receives the newly added transmission a scheduling result of the cluster feedback; the first client interprets and executes the communication configuration code by using a preset interpreter, and the communication configuration code is parsed from the scheduling result according to a communication protocol of the newly added transmission cluster The node identifier of the transmission node scheduled to be newly transmitted by the cluster is transmitted; the first client performs the transmission of the stream data according to the transmission address of the transmission node corresponding to the node identifier.

In this embodiment, the scheduling result of the newly added transmission cluster feedback is the transmission node in the scheduled transmission cluster, and specifically, the newly added transmission cluster schedules a transmission node in the transmission cluster for the first client according to the encapsulated scheduling request. And wherein the scheduling result encapsulates information such as a node identifier of the scheduled transmission node. The transport cluster may allocate a transport node to the client according to the network address and/or the location of the first client, and may further allocate a transport node to the first client according to load balancing among multiple transport nodes, and may specifically adopt any The applicable scheduling mode is not limited in this embodiment. The new transmission cluster sends the scheduling result generated by the scheduling to the first client, and the first client receives the scheduling result.

The node identifier is an identifier of the transit node in the network, and may specifically be an identifier of the transport node in the transport cluster or a network address of the transport node, such as an IP address. The first client interprets and executes the communication configuration code by using a preset interpreter, parses the scheduling result according to the communication protocol of the newly added transmission cluster, and parses out the node identifier of the scheduled transmission node from the scheduling result.

For example, the Lua language universal interpreter is used to interpret and execute the communication configuration code corresponding to the newly added transmission cluster, and the communication configuration code is executed to implement parsing of the IP scheduling result data packet received by the client. Specifically, the content included in the data packet of different transmission cluster IP scheduling results is different. Some transmission clusters agree that the result of the scheduling data packet is the identifier of the stream data directly after the network address of the transmission node, and the specific string, and some transmissions The cluster contract scheduling result packet is a network address of the transport node in a custom format, an identifier of the stream data, and a specific string.

In an embodiment, the transport address is a network address used for streaming data transmission, and may be combined into a transport address by a protocol corresponding protocol header of the stream data transmission, a network address of the transport node, an identifier of the stream data, and an agreed specific string.

The first client can find the corresponding transit node by using the node identifier, and the transport address can be generated on the first client according to the content parsed from the scheduling result, or can be directly parsed from the scheduling result. The first client accesses the transport address and transmits the stream data to the transport node.

In this embodiment, preferably, when the calling the newly added transport cluster, the first client interprets and executes the communication configuration code by using a preset interpreter, according to the communication configuration code Before the communication protocol of the transmission cluster is added to perform the encapsulation of the scheduling request of the transmission node, the method may further include: the first client sending a stream data transmission request to the cluster scheduling server, and receiving the scheduling new feedback from the cluster scheduling server. The feedback result of the transmission cluster.

The cluster scheduling server is a server that can schedule a transmission cluster for the first client, and specifically, the transmission cluster is selected for the first client according to the streaming data transmission request of the first client, and is fed back to the first client. The cluster scheduling server can be a single server or one of the cluster scheduling server clusters. The cluster scheduling server can be the same server as the cluster management server or another server different from the cluster management server.

In this embodiment, the first client sends a stream data transmission request to the cluster scheduling server, where the stream data transmission request usually carries the network address of the client and/or the current location, so as to select the transmission as the cluster scheduling server for the client. The basis of the cluster. The first client receives the feedback result of the cluster scheduling server, where the feedback result is the scheduling result of scheduling the newly added transmission cluster, specifically including the transmission cluster selected for the first client, and may further include the stream data identifier allocated for the stream data. In this embodiment, the cluster scheduling server receives the transmission cluster for the first client as the newly added transmission cluster according to the transmission request of the first client, and the first client receives the feedback result of the cluster scheduling server.

In this embodiment, after the first client determines that there is a newly added transport cluster, the method may further include: the first client acquiring a cluster identifier of the newly added transport cluster; Before the client downloads the corresponding communication configuration code from the communication configuration code base, the method may further include: the first client searching for the corresponding communication configuration code from the communication configuration code base according to the cluster identifier of the newly added transmission cluster. .

After the new transmission cluster is determined, the first client client obtains the cluster identifier of the newly added cluster. For example, the cluster identifier of the newly added cluster can be obtained from the list of the transport cluster. For example, the cluster identity of the newly added transport cluster can be extracted from the first cluster list.

Before downloading the corresponding communication configuration code from the communication configuration code base, the communication configuration code corresponding to the cluster identifier may be searched from the communication configuration code base according to the cluster identifier.

Further, the first client determines that there is a new transmission cluster, and downloads a corresponding communication configuration code from the communication configuration code base, so that when the new transmission cluster provides the streaming data transmission service, the corresponding communication configuration code is directly downloaded for the client. Add the scheduling function of the new transport cluster without adding an application update.

When the first transport cluster is a new transport cluster, the first client interprets and executes the communication configuration code by using a preset interpreter when the new transport cluster is invoked, according to the communication configuration code. The communication protocol of the transmission cluster is added to perform encapsulation of the scheduling request of the transmission node, and the encapsulated scheduling request is sent to the newly added transmission cluster, and the transmission data is transmitted according to the transmission node scheduled by the newly added transmission cluster. The execution of the communication configuration code can complete the encapsulation of the scheduling request corresponding to the newly added transmission cluster, and then is used to schedule the node to schedule the transmission node, thereby implementing the hot update of the scheduling function of the newly added transmission cluster, thereby avoiding the inconvenience and failure of updating the application. .

Referring to FIG. 4, a structural block diagram of a scheduling apparatus for a transport cluster of streaming data according to Embodiment 4 of the present invention is shown, which may specifically include the following modules:

The relationship pre-stored module 401 is configured to pre-store the configuration information of the location information of the client and the at least one transport cluster, where different transport clusters belong to different transport service providers;

The configuration relationship correction module 402 is configured to correct the configuration relationship according to the transmission performance data of the transmission cluster of each transmission service provider;

The cluster scheduling module 403 is configured to schedule a corresponding first transmission cluster for the first client according to the modified configuration relationship;

The cluster notification module 404 is configured to notify the first transmission cluster of the schedule to the first client for transmission of the stream data.

In this embodiment, preferably, the transmission performance data carries a client identifier and a transport cluster identifier corresponding to a single transmission process, where the configuration relationship correction module includes:

An average calculation module, configured to collect transmission performance data of a plurality of clients corresponding to the same location information to the same transmission cluster, and calculate an average value;

The relationship correction module is configured to correct the configuration relationship between the location information and the transport cluster by comparing whether the average value reaches a set threshold, or by comparing an average value of the same location information corresponding to different transport clusters.

In this embodiment, preferably, the device further includes:

a data collection module, configured to collect, before the modification of the configuration relationship, the transmission performance data of the transmission cluster according to each transmission service provider, collecting the transmission reported by multiple clients when performing streaming data transmission with each transmission cluster Performance data, the transmission performance data including a code rate and/or a frame rate.

In this embodiment, preferably, the cluster scheduling module includes:

a cluster search module, configured to search, according to the modified configuration relationship, multiple transport clusters corresponding to the first client;

a first cluster selection module, configured to select, from the plurality of transmission clusters, a first transmission cluster that meets a set condition, where the setting condition includes that the number of historical selections is lower than a set ratio, and the transmission cluster selected in the history is selected. After that, it is greater than the set priority or the transmission performance meets the setting requirements.

In this embodiment, the configuration relationship is a correspondence between a location area where the client is located and a transport cluster, and the cluster scheduling module includes:

An information extraction module, configured to extract network address and/or positioning information of the first client;

An area identifying module, configured to identify, according to the network address and/or the positioning information, a location area to which the first client belongs;

And a searching module, configured to find, according to the configuration relationship, a first transport cluster configured for the identified location area.

In this embodiment, preferably, the device further includes:

a stream data receiving module, configured to receive target stream data uploaded by the first client after the first transmission cluster to be scheduled is notified to the first client, and push the target stream data to store the plurality of transport clusters A storage server that streams data.

In this embodiment, preferably, the device further includes:

The first request receiving module is configured to receive a scheduling request that the second client acquires the target stream data, and notify the first transmission cluster that stores the target stream data to the second client.

In this embodiment, preferably, the device further includes:

a scheduling request replacement module, configured to receive a scheduling request of the second client to replace the first transmission cluster, and schedule a second transmission cluster for the second client according to the configuration relationship, where the second transmission cluster is from the storage server The target stream data is retrieved.

In this embodiment, preferably, the device further includes:

The second request receiving module is configured to receive a scheduling request of the first client to allocate the transport cluster before scheduling the corresponding first transport cluster for the first client according to the modified configuration relationship.

In this embodiment, preferably, the device further includes:

a flow identifier allocation module, configured to: when the scheduling request indicates uploading flow data, assign a flow identifier to the flow data to be uploaded;

The cluster notification module includes:

The transport address notification module is configured to combine the flow identifier with the domain name of the scheduled transport cluster into a streaming address notification to the first client, so that the client performs the transmission of the streaming data according to the streaming address.

In this embodiment, the scheduling request carries the protocol type of the first client, and the transmission address notification module includes:

The transport address component module is configured to combine the stream identifier with a domain name of the scheduled transport cluster into a stream transport address by using the protocol type as a protocol header.

In this embodiment, preferably, the device further includes:

a cluster determining module, configured to determine, by the first client, that a new transport cluster exists before the first transport cluster corresponding to the first client is scheduled according to the modified configuration relationship;

a code downloading module, configured to download, by the first client, a corresponding communication configuration code from the communication configuration code base;

The new transmission cluster is a first transmission cluster, and the device further includes:

a scheduling request encapsulating module, configured to: when the first transmission cluster to be scheduled is notified to the first client, for the transmission of the streaming data, when the newly added transmission cluster is invoked, the first client adopts a preset interpretation Interpreting and executing the communication configuration code, and the communication configuration code performs encapsulation of a scheduling request of the transmission node according to the communication protocol of the newly added transmission cluster;

a scheduling request sending module, configured to send, by the first client, the encapsulated scheduling request to the newly added transport cluster;

The stream data transmission module is configured to transmit, by the first client, the stream data according to the transmission node scheduled by the newly added transmission cluster.

In this embodiment, preferably, the cluster determining module includes:

a list obtaining module, configured to acquire, by the first client, a first cluster list that records all transport clusters from the cluster management server;

The list comparison module is configured to determine, by the first client, that a new transport cluster exists by comparing the first cluster list with the locally stored second cluster list.

In this embodiment, preferably, the device further includes:

a code deletion module, configured to: if the first client determines that there is a deleted target transport cluster by comparing the first cluster list with the locally stored second cluster list, deleting the locally saved target transport cluster Corresponding communication configuration code.

In this embodiment, preferably, the device further includes:

a list update module, configured to update the second cluster list by the first client with the first cluster list of the cluster management server.

In this embodiment, preferably, the communication configuration code further records a network address of the newly added transmission cluster, and the scheduling request sending module includes:

And a request sending module, configured to send, by the first client, the encapsulated scheduling request to the newly added transport cluster according to the network address of the newly added transport cluster indicated by the communication configuration code.

In this embodiment, preferably, the streaming data transmission module includes:

a scheduling result receiving module, configured to receive, by the first client, a scheduling result of the newly added transmission cluster feedback;

a node identifier parsing module, configured, by the first client to interpret and execute the communication configuration code by using a preset interpreter, wherein the communication configuration code is used in the scheduling result according to a communication protocol of the newly added transport cluster Parsing out a node identifier of the transport node scheduled by the newly added transport cluster;

The stream data transmission module is configured to perform, by the first client, the transmission of the stream data according to the transmission address of the transmission node corresponding to the node identifier.

In this embodiment, preferably, the device further includes:

a feedback result receiving module, configured to: when the calling the new transmission cluster is invoked, the first client uses a preset interpreter to interpret and execute the communication configuration code, and the communication configuration code is added according to the Before the communication protocol of the transmission cluster performs encapsulation of the scheduling request of the transmission node, the first client sends a stream data transmission request to the cluster scheduling server, and receives a feedback result of the scheduling new transmission cluster fed back by the cluster scheduling server.

In this embodiment, preferably, the device further includes:

An identifier obtaining module, configured to acquire, after the first client determines that a new transmission cluster exists, the first client acquires a cluster identifier of the newly added transmission cluster;

The device also includes:

a code searching module, configured to: before the first client downloads a corresponding communication configuration code from a communication configuration code base, the first client searches for a communication configuration code base according to a cluster identifier of the newly added transmission cluster Corresponding communication configuration code.

The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general purpose systems can also be used with the teaching based on the teachings herein. The structure required to construct such a system is apparent from the above description. Moreover, the invention is not directed to any particular programming language. It is to be understood that the invention may be embodied in a variety of programming language, and the description of the specific language has been described above in order to disclose the preferred embodiments of the invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that the embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of the description.

Similarly, the various features of the invention are sometimes grouped together into a single embodiment, in the above description of the exemplary embodiments of the invention, Figure, or a description of it. However, the method disclosed is not to be interpreted as reflecting the intention that the claimed invention requires more features than those recited in the claims. Rather, as the following claims reflect, inventive aspects reside in less than all features of the single embodiments disclosed herein. Therefore, the claims following the specific embodiments are hereby explicitly incorporated into the embodiments, and each of the claims as a separate embodiment of the invention.

Those skilled in the art will appreciate that the modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and further they may be divided into a plurality of sub-modules or sub-units or sub-components. In addition to such features and/or at least some of the processes or units being mutually exclusive, any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined. Each feature disclosed in this specification (including the accompanying claims, the abstract and the drawings) may be replaced by alternative features that provide the same, equivalent or similar purpose.

In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features that are included in other embodiments and not in other features, combinations of features of different embodiments are intended to be within the scope of the present invention. Different embodiments are formed and formed. For example, in the following claims, any one of the claimed embodiments can be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the components of the method and apparatus for scheduling a stream of data streams in accordance with embodiments of the present invention. Some or all of the features. The invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for performing some or all of the methods described herein. Such a program implementing the invention may be stored on a computer readable medium or may be in the form of one or more signals. Such signals may be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

For example, Figure 5 illustrates a computing device that can implement a scheduling method for a transport cluster of streaming data in accordance with the present invention. The computing device conventionally includes a processor 510 and a computer program product or computer readable medium in the form of a memory 520. The memory 520 may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), an EPROM, a hard disk, or a ROM. Memory 520 has a memory space 530 for program code 531 for performing any of the method steps described above. For example, storage space 530 for program code may include various program code 531 for implementing various steps in the above methods, respectively. The program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such computer program products are typically portable or fixed storage units as described with reference to FIG. The storage unit may have storage segments, storage spaces, and the like that are similarly arranged to memory 520 in the computing device of FIG. The program code can be compressed, for example, in an appropriate form. Typically, the storage unit includes computer readable code 531 ', ie, code readable by a processor, such as 510, that when executed by a computing device causes the computing device to perform each of the methods described above step.

It is to be noted that the above-described embodiments are illustrative of the invention and are not intended to be limiting, and that the invention may be devised without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as a limitation. The word "comprising" does not exclude the presence of the elements or steps that are not recited in the claims. The word "a" or "an" The invention can be implemented by means of hardware comprising several distinct elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by the same hardware item. The use of the words first, second, and third does not indicate any order. These words can be interpreted as names.

Claims

A scheduling method for a transport cluster of streaming data, comprising:

Pre-storing the location information of the client and the configuration relationship of the at least one transport cluster, wherein different transport clusters belong to different transport service providers;

Correcting the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider;

Scheduling a corresponding first transmission cluster for the first client according to the modified configuration relationship;

The scheduled first transport cluster is notified to the first client for transmission of the streaming data.
The method according to claim 1, wherein the transmission performance data carries a client identifier and a transport cluster identifier corresponding to a transmission process, and the configuration is performed according to transmission performance data of a transport cluster of each transport service provider. The relationship amendments include:

Collecting transmission performance data of multiple clients corresponding to the same location information to the same transmission cluster, and calculating an average value;

The configuration relationship between the location information and the transport cluster is corrected by comparing whether the average value reaches a set threshold or by comparing the same location information to an average of different transport clusters.
The method according to claim 1, wherein before the modifying the configuration relationship according to the transmission performance data of the transmission cluster of each transmission service provider, the method further comprises:

Collecting transmission performance data reported by a plurality of clients when performing streaming data transmission with each transport cluster, the transmission performance data including a code rate and/or a frame rate.
The method according to claim 1, wherein the first transmission cluster corresponding to the first client scheduling according to the modified configuration relationship comprises:

And searching, according to the modified configuration relationship, multiple transmission clusters corresponding to the first client;

Selecting, by the plurality of transmission clusters, a first transmission cluster that satisfies a set condition, where the setting condition includes that the number of historical selections is lower than a set ratio, the ranking is after the historically selected transmission cluster, is greater than a set priority, or Transmission performance meets the set requirements.
The method according to claim 1, wherein the configuration relationship is a correspondence between a location area where the client is located and a transmission cluster, and the first transmission cluster corresponding to the first client scheduling according to the modified configuration relationship includes :

Extracting a network address and/or positioning information of the first client;

Identifying, according to the network address and/or the location information, a location area to which the first client belongs;

According to the configuration relationship, a first transport cluster configured for the identified location area is found.
The method of claim 1, wherein after the notifying the scheduled first transport cluster to the first client, the method further comprises:

Receiving target stream data uploaded by the first client, and pushing the target stream data to a storage server storing stream data of the plurality of transport clusters.
The method of claim 6 wherein the method further comprises:

Receiving a scheduling request of the second client to acquire the target stream data, and notifying the first transmission cluster storing the target stream data to the second client.
The method of claim 7 wherein the method further comprises:

Receiving, by the second client, a scheduling request for replacing the first transport cluster, and scheduling, according to the configuration relationship, a second transport cluster for the second client, where the second transport cluster retrieves the target flow data from the storage server .
The method of claim 1, wherein the method further comprises: before the first configuration of the first transmission cluster is scheduled for the first client according to the modified configuration relationship, the method further comprising:

Receiving a scheduling request of the first client to allocate a transport cluster.
The method of claim 9 wherein the method further comprises:

When the scheduling request indicates that the streaming data is uploaded, the flow identifier is allocated to the streaming data to be uploaded;

The notifying the scheduled first transmission cluster to the first client for transmission of the streaming data includes:

And combining the flow identifier with the domain name of the scheduled transport cluster into a streaming address notification to the first client, so that the client performs the transmission of the streaming data according to the streaming address.
The method of claim 10, wherein the scheduling request carries a protocol type of the first client, and the combining the stream identifier with a domain name of the scheduled transport cluster into a streaming address comprises:

The domain identifier is combined with the domain name of the scheduled transport cluster into a streaming address by using the protocol type as a protocol header.
The method of claim 1, wherein the method further comprises: before the first configuration of the first transmission cluster is scheduled for the first client according to the modified configuration relationship, the method further comprising:

The first client determines that there is a new transport cluster;

The first client downloads a corresponding communication configuration code from the communication configuration code base;

The new transmission cluster is a first transmission cluster. After the first transmission cluster to be notified to the first client for transmission of the stream data, the method further includes:

When the newly added transport cluster is invoked, the first client interprets and executes the communication configuration code by using a preset interpreter, and the communication configuration code performs a scheduling request of the transport node according to the communication protocol of the newly added transport cluster. Package

The first client sends the encapsulated scheduling request to the newly added transport cluster;

The first client performs stream data transmission according to the transmission node scheduled by the newly added transmission cluster.
The method of claim 12, wherein the determining, by the first client, that there is a new transport cluster comprises:

Obtaining, by the first client, a first cluster list that records all transport clusters from the cluster management server;

The first client determines that there is a newly added transport cluster by comparing the first cluster list with the locally stored second cluster list.
The method of claim 13 wherein the method further comprises:

If the first client determines that there is a deleted target transport cluster by comparing the first cluster list with the locally stored second cluster list, the communication configuration code corresponding to the locally saved target transport cluster is deleted.
The method of claim 13 or 14, wherein the method further comprises:

The first client updates the second cluster list with the first cluster list of the cluster management server.
The method of claim 12, wherein the communication configuration code further records a network address of the newly added transmission cluster, and the sending, by the first client, the encapsulated scheduling request to the newly added transmission cluster comprises:

The first client sends the encapsulated scheduling request to the newly added transport cluster according to the network address of the newly added transport cluster indicated by the communication configuration code.
The method according to claim 12, wherein the transmitting, by the first client, the streaming data according to the transmission node scheduled by the newly added transmission cluster comprises:

Receiving, by the first client, a scheduling result of the newly added transmission cluster feedback;

The first client interprets and executes the communication configuration code by using a preset interpreter, and the communication configuration code parses the newly added transmission from the scheduling result according to a communication protocol of the newly added transmission cluster. The node identifier of the transport node of the cluster scheduling;

The first client performs the transmission of the stream data according to the transport address of the transport node corresponding to the node identifier.
The method according to claim 12, wherein, when said invoking said newly added cluster, said first client interprets and executes said communication configuration code by a preset interpreter, said communication configuration code being Before the communication protocol of the newly added transmission cluster is encapsulated by the scheduling request of the transmission node, the method further includes:

The first client sends a stream data transmission request to the cluster scheduling server, and receives a feedback result of the scheduling new transmission cluster fed back by the cluster scheduling server.
The method of claim 12, wherein after the first client determines that there is a new transport cluster, the method further comprises:

Obtaining, by the first client, a cluster identifier of the newly added transport cluster;

Before the first client downloads the corresponding communication configuration code from the communication configuration code base, the method further includes:

The first client searches for a corresponding communication configuration code from the communication configuration code base according to the cluster identifier of the newly added transmission cluster.
A scheduling device for a transport cluster of streaming data, comprising:

The relationship pre-stored module is configured to pre-store the location information of the client and the configuration relationship of the at least one transport cluster, where different transport clusters belong to different transport service providers;

a configuration relationship correction module, configured to modify the configuration relationship according to transmission performance data of a transmission cluster of each transmission service provider;

a cluster scheduling module, configured to schedule, according to the modified configuration relationship, a corresponding first transmission cluster for the first client;

The cluster notification module is configured to notify the first transmission cluster of the schedule to the first client for transmission of the stream data.
The device according to claim 20, wherein the transmission performance data carries a client identifier and a transport cluster identifier corresponding to a one-time transmission process, and the configuration relationship correction module comprises:

An average calculation module, configured to collect transmission performance data of a plurality of clients corresponding to the same location information to the same transmission cluster, and calculate an average value;

The relationship correction module is configured to correct the configuration relationship between the location information and the transport cluster by comparing whether the average value reaches a set threshold, or by comparing an average value of the same location information corresponding to different transport clusters.
The device of claim 20, wherein the device further comprises:

a data collection module, configured to collect, before the modification of the configuration relationship, the transmission performance data of the transmission cluster according to each transmission service provider, collecting the transmission reported by multiple clients when performing streaming data transmission with each transmission cluster Performance data, the transmission performance data including a code rate and/or a frame rate.
The apparatus of claim 20, wherein the cluster scheduling module comprises:

a cluster search module, configured to search, according to the modified configuration relationship, multiple transport clusters corresponding to the first client;

a first cluster selection module, configured to select, from the plurality of transmission clusters, a first transmission cluster that meets a set condition, where the setting condition includes that the number of historical selections is lower than a set ratio, and the transmission cluster selected in the history is selected. After that, it is greater than the set priority or the transmission performance meets the setting requirements.
The device according to claim 20, wherein the configuration relationship is a correspondence between a location area where the client is located and a transport cluster, and the cluster scheduling module includes:

An information extraction module, configured to extract network address and/or positioning information of the first client;

An area identifying module, configured to identify, according to the network address and/or the positioning information, a location area to which the first client belongs;

And a searching module, configured to find, according to the configuration relationship, a first transport cluster configured for the identified location area.
The device of claim 20, wherein the device further comprises:

a stream data receiving module, configured to receive target stream data uploaded by the first client after the first transmission cluster to be scheduled is notified to the first client, and push the target stream data to store the plurality of transport clusters A storage server that streams data.
The device of claim 25, wherein the device further comprises:

The first request receiving module is configured to receive a scheduling request that the second client acquires the target stream data, and notify the first transmission cluster that stores the target stream data to the second client.
The device of claim 26, wherein the device further comprises:

a scheduling request replacement module, configured to receive a scheduling request of the second client to replace the first transmission cluster, and schedule a second transmission cluster for the second client according to the configuration relationship, where the second transmission cluster is from the storage server The target stream data is retrieved.
The device of claim 20, wherein the device further comprises:

The second request receiving module is configured to receive a scheduling request of the first client to allocate the transport cluster before scheduling the corresponding first transport cluster for the first client according to the modified configuration relationship.
The device of claim 28, wherein the device further comprises:

a flow identifier allocation module, configured to: when the scheduling request indicates uploading flow data, assign a flow identifier to the flow data to be uploaded;

The cluster notification module includes:

The transport address notification module is configured to combine the flow identifier with the domain name of the scheduled transport cluster into a streaming address notification to the first client, so that the client performs the transmission of the streaming data according to the streaming address.
The apparatus according to claim 29, wherein the scheduling request carries a protocol type of the first client, and the transmission address notification module comprises:

The transport address component module is configured to combine the stream identifier with a domain name of the scheduled transport cluster into a stream transport address by using the protocol type as a protocol header.
The device of claim 20, wherein the device further comprises:

a cluster determining module, configured to determine, by the first client, that a new transport cluster exists before the first transport cluster corresponding to the first client is scheduled according to the modified configuration relationship;

a code downloading module, configured to download, by the first client, a corresponding communication configuration code from the communication configuration code base;

The new transmission cluster is a first transmission cluster, and the device further includes:

a scheduling request encapsulating module, configured to: when the first transmission cluster to be scheduled is notified to the first client, for the transmission of the streaming data, when the newly added transmission cluster is invoked, the first client adopts a preset interpretation Interpreting and executing the communication configuration code, and the communication configuration code performs encapsulation of a scheduling request of the transmission node according to the communication protocol of the newly added transmission cluster;

a scheduling request sending module, configured to send, by the first client, the encapsulated scheduling request to the newly added transport cluster;

The stream data transmission module is configured to transmit, by the first client, the stream data according to the transmission node scheduled by the newly added transmission cluster.
The apparatus of claim 31, wherein the cluster determination module comprises:

a list obtaining module, configured to acquire, by the first client, a first cluster list that records all transport clusters from the cluster management server;

The list comparison module is configured to determine, by the first client, that a new transport cluster exists by comparing the first cluster list with the locally stored second cluster list.
The device of claim 32, wherein the device further comprises:

a code deletion module, configured to: if the first client determines that there is a deleted target transport cluster by comparing the first cluster list with the locally stored second cluster list, deleting the locally saved target transport cluster Corresponding communication configuration code.
The device of claim 32 or 33, wherein the device further comprises:

a list update module, configured to update the second cluster list by the first client with the first cluster list of the cluster management server.
The device according to claim 31, wherein the communication configuration code further records a network address of the newly added transmission cluster, and the scheduling request sending module includes:

And a request sending module, configured to send, by the first client, the encapsulated scheduling request to the newly added transport cluster according to the network address of the newly added transport cluster indicated by the communication configuration code.
The apparatus of claim 31, wherein the streaming data transmission module comprises:

a scheduling result receiving module, configured to receive, by the first client, a scheduling result of the newly added transmission cluster feedback;

a node identifier parsing module, configured, by the first client to interpret and execute the communication configuration code by using a preset interpreter, wherein the communication configuration code is used in the scheduling result according to a communication protocol of the newly added transport cluster Parsing out a node identifier of the transport node scheduled by the newly added transport cluster;

The stream data transmission module is configured to perform, by the first client, the transmission of the stream data according to the transmission address of the transmission node corresponding to the node identifier.
The device of claim 31, wherein the device further comprises:

a feedback result receiving module, configured to: when the calling the new transmission cluster is invoked, the first client uses a preset interpreter to interpret and execute the communication configuration code, and the communication configuration code is added according to the Before the communication protocol of the transmission cluster performs encapsulation of the scheduling request of the transmission node, the first client sends a stream data transmission request to the cluster scheduling server, and receives a feedback result of the scheduling new transmission cluster fed back by the cluster scheduling server.
The device of claim 31, wherein the device further comprises:

An identifier obtaining module, configured to acquire, after the first client determines that a new transmission cluster exists, the first client acquires a cluster identifier of the newly added transmission cluster;

The device also includes:

a code searching module, configured to: before the first client downloads a corresponding communication configuration code from a communication configuration code base, the first client searches for a communication configuration code base according to a cluster identifier of the newly added transmission cluster Corresponding communication configuration code.
A computer program comprising computer readable code, when said computer readable code is run on a computing device, causing said computing device to perform a transport cluster of streaming data according to any of claims 1-19 Scheduling method.
A computer readable medium storing the computer program of claim 39.