CN116744024A

CN116744024A - Request processing method, request processing device, live broadcast data processing method and live broadcast data processing system

Info

Publication number: CN116744024A
Application number: CN202310646278.5A
Authority: CN
Inventors: 陈鹏; 程伟华; 肖凯; 但瑜
Original assignee: Alibaba China Co Ltd
Current assignee: Alibaba China Co Ltd
Priority date: 2023-06-01
Filing date: 2023-06-01
Publication date: 2023-09-12

Abstract

The embodiment of the application provides a request processing method and device, comprising the following steps: receiving a first resource acquisition request sent by terminal equipment; acquiring request information according to the first resource; acquiring node information of resource nodes in a resource cluster; determining a scheduling weight value of a resource node according to the request information of the first resource acquisition request and the node information of the resource node; selecting a target resource node with a scheduling weight value meeting a preset weight condition from the resource node information; based on the communication information of the target resource node, generating a redirection response for the first resource acquisition request; sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target resource node based on the communication information of the target resource node in the redirection response so as to acquire the resource data.

Description

Request processing method, request processing device, live broadcast data processing method and live broadcast data processing system

Technical Field

The present application relates to the field of computer technologies, and in particular, to a request processing method, a request processing device, a live broadcast data processing method, a system electronic device, and a machine readable medium.

Background

In the scenario related to data acquisition, the processing procedure of the request sent by the server to the terminal device often uses 302 scheduling, where 302 scheduling is scheduling for redirecting by using 302 response as a carrier, and the 302 response is a special redirecting response. For example, a terminal device sends a resource acquisition request to a server, the server can send the 302 response to the terminal device according to the resource acquisition request, the 302 response includes a special status code (302) and a new address of a new server, so that the terminal device re-requests a re-scheduling method of the new server according to the new address, the 302 scheduling can greatly improve the resource utilization efficiency of the server, each resource node receiving the resource acquisition request does not need to go to a data source to acquire resource data, and the 302 scheduling mode can reduce the number of resource nodes which go to the data source to acquire the resource data, thereby saving the bandwidth of the resource cluster.

At present, a server is regarded as a resource node, a plurality of resource rings exist in a scene according to the setting of a scheduling policy, the resource rings are regarded as a set containing a plurality of resource nodes, in order to realize 302 scheduling, the resource rings can be constructed as hash rings based on the scheduling policy acquired from a scheduling policy maintenance end, one hash value on the hash rings corresponds to one resource node in the characterization resource rings, after the hash rings are constructed, a resource acquisition request is sent to a terminal device, if the resource acquisition request needs 302 scheduling, the hash value can be calculated based on the request information of the request, then the hash value of the request information is matched on the hash value on the hash rings, a target resource node can be obtained after the matching, then a new address of the target resource node is returned to the terminal device based on 302 response, and the terminal device revisits the new address to acquire resource data, thereby realizing 302 scheduling.

However, the inventor finds that in the current scheme, the scheduling policy is in a frequent change scene, so that each time the scheduling policy is updated, a resource ring is changed, and a corresponding hash ring needs to be reconstructed, which results in a large cost.

Disclosure of Invention

The embodiment of the application provides a request processing method, which aims to solve the problem that a corresponding hash ring is frequently reconstructed in the related art, so that larger expenditure is generated.

Correspondingly, the embodiment of the application also provides a request processing device, electronic equipment and a storage medium, which are used for ensuring the realization and the application of the method.

In order to solve the above problems, an embodiment of the present application discloses a request processing method, which includes: receiving a first resource acquisition request sent by terminal equipment;

acquiring request information according to the first resource acquisition request;

acquiring node information of resource nodes in a resource cluster;

determining a scheduling weight value of the resource node according to request information of a first resource acquisition request and node information of the resource node;

selecting a target resource node with a scheduling weight value meeting a preset weight condition from the resource node information;

Generating a redirection response to the first resource acquisition request based on the communication information of the target resource node;

sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target resource node based on the communication information of the target resource node in the redirection response so as to acquire resource data.

The embodiment of the application also discloses a live broadcast data processing method, which comprises the following steps:

receiving a first direct broadcast data acquisition request sent by terminal equipment;

acquiring request information according to the first direct broadcast data acquisition request;

acquiring node information of live broadcast resource nodes in a live broadcast cluster;

determining a scheduling weight value of the live broadcast resource node according to the request information and the node information of the live broadcast resource node;

selecting a target live broadcast resource node with a scheduling weight value meeting a preset weight condition from the live broadcast resource node information;

generating a redirection response for the first resource acquisition request based on the communication information of the target live broadcast resource node;

sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target live broadcast resource node based on the communication information of the target live broadcast resource node in the redirection response so as to acquire live broadcast data.

The embodiment of the application discloses a request processing device, which comprises:

the first request receiving module is used for receiving a first resource acquisition request sent by the terminal equipment;

the first request information acquisition module is used for acquiring request information according to the first resource acquisition request;

the first node information acquisition module is used for acquiring node information of resource nodes in the resource cluster;

the first scheduling determining module is used for determining a scheduling weight value of the resource node according to the request information of the first resource acquisition request and the node information of the resource node;

the first node selection module is used for selecting a target resource node of which the scheduling weight value meets a preset weight condition from the resource node information;

a first response generation module, configured to generate a redirection response for the first resource acquisition request based on the communication information of the target resource node;

the first response sending module is used for sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target resource node based on the communication information of the target resource node in the redirection response so as to acquire resource data.

The embodiment of the application discloses a request data acquisition request processing system in a live broadcast scene, which comprises the following components: a live broadcast resource cluster, wherein the live broadcast resource cluster comprises a plurality of live broadcast resource nodes;

the first direct broadcast resource node of the direct broadcast resource cluster includes:

the second request receiving module is used for receiving a first resource acquisition request sent by the terminal equipment;

the second request information acquisition module is used for acquiring request information according to the first direct broadcast data acquisition request;

the second node information acquisition module is used for acquiring node information of live broadcast resource nodes in the live broadcast cluster;

the second scheduling determining module is used for determining a scheduling weight value of the live broadcast resource node according to the request information and the node information of the live broadcast resource node;

the live broadcast resource node selection module is used for selecting a target live broadcast resource node with a scheduling weight value meeting a preset weight condition from the live broadcast resource node information;

a second response generation module, configured to generate a redirection response for the first resource acquisition request based on the communication information of the target live broadcast resource node;

the second response sending module is used for sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target live broadcast resource node based on the communication information of the target live broadcast resource node in the redirection response so as to acquire live broadcast data;

The target live broadcast resource node is used for: and processing the second resource acquisition request and sending live broadcast data to the terminal equipment.

Live broadcast resource node live broadcast resource live resource node live live resource node

The embodiment of the application also discloses an electronic device, which comprises: a processor; and a memory having executable code stored thereon that, when executed, causes the processor to perform a method as described in one or more of the embodiments of the application.

Embodiments of the application also disclose one or more machine-readable media having executable code stored thereon that, when executed, cause a processor to perform a method as described in one or more of the embodiments of the application.

Compared with the related art, the embodiment of the application has the following advantages:

in the process of resource acquisition request, the resource node in the resource cluster can calculate the scheduling weight value of the resource node on line, select the target resource node based on the scheduling weight value, generate a redirection response for the first resource acquisition request based on the communication information of the target resource node and return the terminal equipment, so that the terminal equipment sends a second resource acquisition request to the target resource node to acquire resource data based on the target resource node, 302 scheduling is realized.

Drawings

FIG. 1 is a system architecture diagram of an embodiment of the present application;

fig. 2 is a schematic diagram of a live video scene according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a file download scenario according to an embodiment of the present application;

fig. 4 is a schematic view of a multimedia file on demand scene according to an embodiment of the present application;

FIG. 5 is a flow chart of steps of a request processing method according to an embodiment of the present application;

FIG. 6 is a flowchart illustrating steps of a request processing method according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a hash matching process according to an embodiment of the present application;

FIG. 8 is a flowchart illustrating steps of a method for processing live data according to an embodiment of the present application;

FIG. 9 is a block diagram of a request processing apparatus according to an embodiment of the present application;

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

Detailed Description

In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description.

For a better understanding of the present application, the following description is given to illustrate the concepts related to the present application to those skilled in the art:

302 scheduling: 302 respond to a schedule for redirection as a bearer. The terminal device requests the server, the server does not normally respond to the request to return the resource data, but sends a redirection response comprising the special state code (302) and the new address to the terminal device, the terminal device re-requests the new server according to the special state code (302) and the new address, and the new server responds to the new request of the terminal device to return the resource data. In the data acquisition scene, if the requests of all the terminal devices are randomly distributed on a plurality of service terminals to respond, the service terminals need to acquire data from the same data source to feed back to the terminal devices when responding to the requests, so that more service terminals perform data source returning (namely acquire data from the data source), internal bandwidth waste is caused, the cost of the data source returning is high, and the 302 scheduling schedules the requests of the terminal devices to some 302 nodes to process, and the 302 nodes process the requests of all the terminal devices and complete the data source returning, thereby greatly reducing the internal bandwidth and the cost of the data source returning.

302 node: i.e. the new resource node corresponding to the new address carried by the resource node in response to the status code (302).

Data source return: refers to the process by which a resource node obtains data from a data source for return to a terminal device.

Resource acquisition request: a request initiated by the terminal device and processed by the resource node. Under the condition that the terminal equipment sends a resource acquisition request to the resource node when the terminal equipment requests to acquire the data in the data source, and the resource node responds to the resource acquisition request to acquire the data from the data source and feeds the data back to the terminal equipment so as to realize data source returning. Specifically, in the process that the terminal device sends the resource obtaining request to the resource node, the terminal device may send the access request to a domain name system (DNS, domain Name Server) server, and the DNS server may send an internet protocol (IP, internet Protocol) address of the resource node to the terminal device after resolving the access request, so that the terminal device may send the resource obtaining request to the resource node based on the IP address of the resource node. In the embodiment of the application, the resource acquisition request can comprise a live broadcast data acquisition request, a video acquisition request, an audio acquisition request and the like.

Request information of resource acquisition request: and the server receives the relevant information corresponding to the request. Taking HTTP (HyperText Transfer Protocol ) protocol as an example, HTTP requests such as get requests and post requests sent by a terminal device are classified into contents such as request header and request line. The HTTP request message carries a uniform resource locator (URL, uniform Resource Locator). In an example, the request information of the embodiment of the present application may be a URL obtained from an HTTP request message.

Presetting a scheduling condition: it is determined whether the resource acquisition request sent by the terminal device may be adjusted for scheduling 302. Under the condition, the preset scheduling condition may be defined as determining the resource popularity of the resource acquisition request (for example, in a live video scene, the resource popularity may be determined according to the number of players requested), if the resource popularity is smaller, the request may be scheduled 302, and if the resource popularity is larger, the request may not be scheduled 302 (the traffic of the request with larger popularity is concentrated on the 302 node, which may cause the excessive load of the 302 node).

Resource cluster: the resource cluster can be constructed based on the scheduling policy of an operator-region in a live broadcast scene, for example, in Zhejiang, a batch of resource nodes of an operator for telecommunication can be constructed as one resource cluster, in Hebei, and a batch of resource nodes of an operator for communication can be constructed as another resource cluster.

Resource node: the carrier with the capability of computing and processing tasks can be a physical machine or a virtual machine.

Node information: node attribute information such as node names and initial weights set for the resource nodes.

Scheduling weight value: the parameter reflecting the probability that the resource node can be used as the 302 node is the positive correlation between the scheduling weight value and the probability that the resource node can be used as the 302 node. The scheduling weight value may be calculated by a calculation formula reflecting that the larger the initial weight, the greater the probability that a resource node is selected as a 302 node.

And (3) hash calculation: a calculation mode realized by utilizing a hash function can use text to generate codes called message digests, so that digital authentication of the text information is realized, namely, a corresponding mathematical form hash value can be obtained by carrying out hash calculation on the text information, and the text information has a representation of the mathematical form.

Hash ring: the ring data structure constructed based on the consistent hash algorithm, specifically, the consistent hash algorithm organizes the whole hash value space into a virtual ring according to the clockwise/anticlockwise direction, hash values corresponding to the resource nodes can be distributed on the hash ring, one hash value on the hash ring corresponds to one resource node representing the resource ring, after the hash ring is constructed, the hash value of the request can be calculated aiming at a request meeting 302 scheduling sent by the terminal equipment, and a target hash value matched with the hash value of the request on the hash ring is determined, so that the target resource node corresponding to the target hash value is determined as the 302 node.

The request processing method in the embodiment of the application can be applied to the scenario that the terminal equipment sends a request to the resource node to request to acquire the corresponding data in the data source, and the application scenario can comprise: video live scenes, file download scenes, multimedia file on-demand scenes, and the like. Taking a live video scene as an example, when a terminal device views live video, a live video room can be selected to view, at the moment, the terminal device triggers an operation of sending a resource acquisition request to a first resource node, when the resource acquisition request meets the condition of 302 scheduling, the embodiment of the application can calculate the scheduling weight value of the resource node according to the content information of the resource acquisition request and the node information of the resource node in a resource cluster, and send the communication information of a target resource node with the scheduling weight value meeting the preset weight condition to the terminal device, so that the terminal device sends a second resource acquisition request to the target resource node according to the communication information of the target resource node, realizes data source return by the target resource node, acquires live video resources from the data source and feeds back to the terminal device.

Referring to fig. 1, a system architecture diagram of a request processing method according to an embodiment of the present application is shown, including: the system comprises terminal equipment, a resource cluster, a data source and a scheduling policy maintenance terminal, wherein the resource cluster comprises a plurality of resource nodes. The terminal device is configured to execute S1, access a first resource node, specifically send a resource acquisition request to the first resource node in the resource cluster, where the purpose of the resource acquisition request is to acquire corresponding data from a data source and send the data to the terminal device, where the first resource node may calculate a scheduling weight value of each resource node when determining that the resource acquisition request is a request that needs to be scheduled 302, then execute S2, send the determined communication information of the target resource node to the terminal device, so as to implement adding a status code (302) and the communication information of the target resource node to a response to the resource acquisition request, and finally the terminal device may execute S3, revisit the target resource node according to the status code (302), specifically send a second resource acquisition request to the target resource node according to the communication information of the target resource node, execute the second resource acquisition request by the target resource node, thereby implementing data source return, execute S4, acquire resources from the data source and feed back to the terminal device. It should be noted that, the determination of the first resource node that is the object of the first sending of the resource acquisition request by the terminal device is implemented based on a preset scheduling scheme, where the preset scheduling scheme specifically includes a scheme for implementing request scheduling, such as a load balancing scheme, and the embodiment of the present application is not limited in this way specifically.

The scheduling policy maintenance end can periodically synchronize the scheduling policy to each resource node in the resource cluster. The system maintainer can adjust the scheduling policy based on the scheduling policy maintenance end, such as adding and deleting resource nodes, changing the initial weight value of the resource nodes, and the like.

Specifically, in the case that the first resource node determines that the resource acquisition request is a resource acquisition request that needs to be scheduled 302, the first resource node may calculate a scheduling weight value of the resource node according to the request information of the resource acquisition request and the node information of the resource node, and the calculation of the scheduling weight value may specifically perform hash calculation on a joint result of a node name of the resource node and all or part of the request information of the resource acquisition request to obtain a first hash result, and then calculate the scheduling weight value of the resource node according to the first hash result of the resource node, an initial weight of the resource node, and a hash range set for the hash calculation, where a specific calculation process may adopt the following formula 1:

equation 1: si=wi/In (hash_max/xi);

where si is a scheduling weight value of the resource node i, wi is an initial weight of the resource node i, hash_max is an upper limit value of a HASH range set for HASH calculation, xi is a first HASH result of the resource node i, and In is a natural logarithm operator.

In the embodiment of the application, the scheduling weight value reflects the probability that the resource node can be used as the 302 node, and the process of obtaining the scheduling weight value of the resource node through the formula 1 reflects the probability that the resource node with larger initial weight is selected as the 302 node.

Therefore, the first resource node 302 may select, according to the calculated scheduling weight value of each resource node, a resource node whose node hash value is greater than that of other resource nodes, as a target resource node, and send the communication information of the target resource node and the status code (302) to the terminal device, so as to implement 302 scheduling.

The embodiment of the application can calculate the scheduling weight value of the resource node on line in the process of processing the processing request of the generation meeting the 302 scheduling policy, select the target resource node based on the scheduling weight value, add the communication information of the target resource node to the response aiming at the resource acquisition request, so that the terminal equipment sends the second resource acquisition request to the target resource node to realize 302 scheduling.

It should be noted that, according to the method for processing a request provided by the embodiment of the present application, several specific scenarios may be implemented as follows:

in one implementation manner, referring to fig. 2, a schematic view of a live video scene provided by an embodiment of the present application is shown, including: the terminal equipment can initiate a live broadcast resource acquisition request to a first live broadcast resource node in the live broadcast resource cluster, the first live broadcast resource node can calculate the scheduling weight value of each live broadcast resource node under the condition that the live broadcast resource acquisition request is judged to be a request needing to be scheduled by 302, then a second live broadcast resource node with the scheduling weight value meeting a preset weight condition is used as a target live broadcast resource node, communication information of a state code (302) and the second live broadcast resource node is added to a 302 response aiming at the resource acquisition request, finally the terminal equipment can send a new live broadcast resource acquisition request to the second live broadcast resource node according to the communication information of the second live broadcast resource node by the state code (302), the second live broadcast resource node executes the new live broadcast resource acquisition request, acquires corresponding data from the data source and feeds the corresponding data back to the terminal equipment, the whole 302 scheduling process omits offline construction of a ring and hash ring matching, and the hash ring reconstruction cost is greatly reduced under the condition of the hash ring.

In another implementation manner, referring to fig. 3, a schematic diagram of a file download scenario provided by an embodiment of the present application is shown, including: the terminal equipment can initiate a file downloading request to a first file resource node in the file resource cluster, the first file resource node can calculate the scheduling weight value of each file resource node under the condition that the first file resource node judges that the file downloading request is a request needing to be scheduled by 302, then the second file resource node with the scheduling weight value meeting the preset weight condition is used as a target file resource node, the state code (302) and the communication information of the second file resource node are added to a response to the file resource obtaining request 302, finally the terminal equipment can send a new file downloading request to the second file resource node according to the communication information of the second file resource node according to the state code (302), the second file resource node executes the new file downloading request, acquires corresponding file resource data from the data source and feeds back to the terminal equipment, the whole scheduling process is realized, the construction of an offline loop and the hash loop matching are omitted, and the hash loop is greatly saved under the condition of the hash loop is replaced.

In another implementation manner, referring to fig. 4, a schematic view of a multimedia file on-demand scene provided by an embodiment of the present application is shown, including: the terminal equipment can send a new request to the second multimedia resource node according to the communication information of the second multimedia resource node, the second multimedia resource node executes the new request, acquires corresponding multimedia resource data from the data source and feeds the data back to the terminal equipment, and the whole 302 scheduling process omits an offline construction hash ring and a hash ring, thereby reducing the reconstruction cost of the hash ring under the condition of more frequent reconstruction.

It should be noted that, the user information (including but not limited to terminal equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

Referring to fig. 5, a flowchart of steps of a request processing method according to an embodiment of the present application is shown, including:

step 101, receiving a first resource acquisition request sent by a terminal device;

in many scenarios, the terminal device needs to send a resource acquisition request to a certain resource node in the resource cluster, so as to request the resource node to provide a corresponding service, where the resource node that receives the first resource acquisition request may be defined as a first resource node. The first resource obtaining request may be a resource obtaining request triggered by the terminal device for the first time, for example, a resource obtaining request triggered by a user opening a living broadcast room.

It should be noted that, taking an HTTP request as an example, the terminal device triggers an HTTP request for a certain URL, the terminal device may first send a DNS request to a DNS server based on the URL, the DNS server analyzes an IP address of a resource node corresponding to the URL, returns the IP address to the terminal device, and then the terminal device sends the HTTP request to the resource node corresponding to the IP address. Taking the get request as an example, for an http:// domain.com/app/stream URL, the format of the get request is as follows:

GET/app/stream HTTP/1.1

User-Agent:abc

Host:domain.com

Accept-Language:en,mi

the first action request type GET, the path/app/stream of the URL and the protocol version number HTTP/1.1. The second behavioural user agent identification. And a third behavioral master domain name domain.com, a fourth behavioral language type. Of course, the request may also include other fields, which embodiments of the present application do not limit.

After receiving the request, the resource node can acquire request information from the request, specifically, can extract relevant information from the request according to requirements, and then assemble the relevant information according to preset rules to acquire the request information. For example, in the above example, the main domain name domain/com may be extracted from the first row, and the http:// domain name/com/app/stream may be obtained by splicing according to the organization rule of the URL.

Step 102, acquiring request information according to the first resource acquisition request;

because the identity of the resource node is the server, after the terminal equipment sends the first resource acquisition request, the server receives the request in a corresponding format, and then the server can acquire the request information from the first resource acquisition request based on a corresponding protocol.

As in the previous example, the resource node may obtain, based on the HTTP protocol, the URL that the terminal device wants to access as the request information to be processed, and the http:// domain. In order to facilitate the subsequent processing, in the embodiment of the present application, the acquired request information may include a URL, and because the URL corresponds to the resource data, the URL may be more accurately located to the resource data, so as to acquire relevant information, such as heat information, of the resource data. Of course, other content in the request may be included, and embodiments of the present application are not limited thereto.

Step 103, obtaining node information of resource nodes in the resource cluster.

First, the implementation manner and meaning of 302 scheduling in the scenario of the embodiment of the present application are explained: the 302 scheduling refers to that the terminal equipment requests the service end, the service end does not respond to the request, but sends a special state code (302) and a new address to the terminal equipment, the terminal equipment re-requests the new service end according to the special state code (302) and the new address, the new service end responds to the new request process of the terminal equipment, the 302 scheduling can schedule the request of the terminal equipment to a fixed 302 node for processing, and the 302 node comprehensively processes the request of each terminal equipment and completes data source return, so that the internal bandwidth is greatly reduced, and the data source return cost is reduced.

Further by way of one example, the description of 302 the scheduling effect: assuming that a plurality of resource nodes exist in the region of Zhejiang province, if 302 scheduling is not performed, the requests generated by terminal equipment in Zhejiang province are randomly distributed on each resource node to be responded and executed, so that a plurality of resource nodes simultaneously exist for data source returning, and the internal bandwidth is overlarge; if 302 scheduling is performed, the request generated by the terminal equipment in Zhejiang province is concentrated on a resource node serving as a 302 node to be responded and executed, and only the resource node serving as the 302 node performs data source returning, so that the internal bandwidth cost is saved.

In the embodiment of the present application, in order to perform 302 scheduling, node information of some or all resource nodes in the resource cluster needs to be acquired online.

In the embodiment of the present application, the resource node that receives the resource acquisition request sent by the terminal device in step 101 may first determine whether the resource acquisition request is a request that needs to be scheduled 302, and the determination principle may be defined as determining the resource heat of the resource acquisition request (e.g., the resource heat may be determined according to the number of players requested in a live video scene), if the resource heat is smaller, the request may be scheduled 302, and if the resource heat is larger, the request may not be scheduled 302, so as to avoid too large load of the target resource node. In addition, in response to the 302 schedule, first, it is required to determine the target resource node that can be used as the 302 node from the resource cluster, and then step 102 needs to obtain node information of the resource nodes in the resource cluster, so that the target resource node that can be used as the 302 node is determined by an online computing manner.

It should be noted that the order between the step 102 and the step 103 is not limited by the embodiment of the present application.

And 104, calculating a scheduling weight value of the resource node according to the content information of the resource acquisition request and the node information of the resource node.

In the embodiment of the present application, in step 101, a resource node that receives a resource acquisition request sent by a terminal device may calculate a scheduling weight value of the resource node according to content information of the resource acquisition request and node information of the resource node, a specific calculation process may introduce a hash algorithm and an initial weight preset for each resource node, and the hash algorithm may use text to generate a code called an information abstract, so as to implement digital authentication of text information, so that the text-form node information and information have a mathematical form of representation, in addition, the calculated scheduling weight value may be a parameter reflecting the probability that the resource node can be used as a 302 node, and the process of calculating the scheduling weight value reflects that the larger the initial weight is the larger the probability that the resource node is selected as the 302 node.

Therefore, according to the embodiment of the application, the scheduling weight value of the resource node is obtained in an online calculation mode according to the content information of the resource acquisition request and the node information of the resource node, so that the judgment of whether the resource node can be selected as the 302 node is realized, and the quantization of specific numerical values is realized.

And 105, selecting a target resource node with a scheduling weight value meeting a preset weight condition from the resource node information.

In the embodiment of the application, as the scheduling weight value of each resource node is calculated, one target resource node can be selected from each resource node based on a preset weight condition and used as a 302 node for the terminal equipment to revisit to acquire the resource data.

And 106, generating a redirection response for the first resource acquisition request based on the communication information of the target resource node.

In the embodiment of the present application, since the scheduling is to be performed 302, the first resource node does not normally respond to the first resource acquisition request, and does not acquire the resource data from the server where the data source is located, and returns the resource data to the terminal device, but generates a redirection response, for example, a 302 response, and then carries the communication information of the redirected target resource node in the response and returns the communication information to the terminal device.

In practical application, the communication information of the target resource node with the scheduling weight value meeting the preset weight condition may be added to the 302 response to the first resource acquisition request.

The generated redirect response, for example the HTTP protocol, may write 302 a status code in the status line of the message and then add the communication information to the response body, for example to the body tag of the message.

Step 107, sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target resource node based on the communication information of the target resource node in the redirection response so as to acquire resource data.

After obtaining the 3 redirection response through the foregoing steps, the first resource node sends the response to the terminal device. After receiving the response, the terminal device may parse the message based on the HTTP protocol, parse and find that the message is a 302 response, extract the communication information of the target resource node from the response text of the message, and then send a second resource acquisition request to the target resource node based on the communication information. The second resource acquisition request may be understood as a redirect request.

After receiving the second resource obtaining request, the target resource node can obtain the resource data from the server where the data source is located, and then returns to the terminal device.

In practical application, when the terminal device sends the second resource acquisition request, the request may carry the redirection identifier, after receiving the second resource acquisition request, the target resource node analyzes the resource address and the redirection identifier, and then it may be determined that the redirection identifier exists in the request, and 302 scheduling may not be performed any more, and the resource data may be directly obtained from a data source where the resource data required by the resource address is located, and then the resource data is sent to the terminal device, so that each resource acquisition request is prevented from being constantly scheduled 302.

In the embodiment of the present application, because the obtained scheduling weight value of the resource node is calculated, whether the resource node can be selected as the 302 node is determined, and the specific numerical value is quantized, in step 101, the resource node receiving the resource acquisition request sent by the terminal device may use the target resource node whose scheduling weight value meets the preset weight condition as the 302 node, add the status code (302) and the communication information of the target resource node to the response to the resource acquisition request, and the subsequent terminal device may send the second resource acquisition request to the target resource node according to the communication information of the target resource node, and execute the second resource acquisition request by the target resource node, thereby implementing data source return, and acquire the live broadcast resource from the data source and feed back to the terminal device.

In summary, in the embodiment of the present application, in the process of processing a processing request of a generation meeting a 302 scheduling policy, a scheduling weight value of a resource node is calculated online, a target resource node is selected based on the scheduling weight value, and communication information of the target resource node is added to a response to a resource acquisition request, so that a terminal device sends a second resource acquisition request to the target resource node, and 302 scheduling is implemented.

Referring to fig. 6, a flowchart illustrating specific steps of a request processing method according to an embodiment of the present application is shown, including:

step 201, receiving a first resource acquisition request sent by a terminal device;

this step may refer to step 101, and is not described herein.

Step 202, acquiring request information according to the first resource acquisition request;

this step may refer to step 102, and is not described herein.

Step 203, obtaining resource scheduling environment information;

optionally, the resource scheduling context information includes: at least one of resource heat of resource data corresponding to the first resource obtaining request, update frequency of the resource cluster and average number of resource nodes in a resource group; wherein the resource group is composed of at least one resource node in the resource cluster.

In the embodiment of the application, the resource heat of the first resource acquisition request, the update frequency of the resource cluster and the average number of the resource nodes in the resource group can be acquired.

Wherein, part of the resource nodes in the resource cluster form a resource group. A resource cluster may have at least one resource group, such as 1 resource group, 2 resource groups, 3 resource groups, etc. Each resource group may have at least one resource node, such as 1 resource node, 2 resource nodes, 3 resource nodes, etc.

In the embodiment of the present application, a resource node that receives a first resource acquisition request sent by a terminal device needs to determine whether the first resource acquisition request is a request that needs to be scheduled on line 302, and the determining process may be implemented by analyzing the resource heat of the first resource acquisition request, the update frequency of a resource cluster, and the average number of resource nodes in a resource group. Of course, one or more of these three may be used in the analysis process, and embodiments of the present application are not limited thereto.

The resource popularity of the resource acquisition request may be specifically defined as: for the usage amount of the resource data requested to be acquired by the resource acquisition request, for example, in a live video scene, the resource heat degree can be determined by the number of players of the live video stream requested to be acquired by the resource acquisition request, and the resource heat degree and the number of players are in positive correlation).

In practical application, the resource cluster is updated along with the change of the practical requirement, and the update of the resource cluster refers to the occurrence of the situations of adding, deleting, changing and the like of the resource nodes. In addition, a plurality of resource nodes can be selected to form a resource group according to the actual service requirement in the resource cluster, a plurality of resource groups can exist in the resource cluster at the same time,

For example, assuming that 7 resource nodes of a (Zhejiang-mobile), b (Zhejiang-mobile), c (Hebei-UNICOM), d (Hebei-UNICOM), e (Hebei-UNICOM), f (Shaanxi-telecom), g (Shaanxi-telecom) exist in the resource cluster, the resource nodes have corresponding areas and operators, the resource group 1 can be divided into resource nodes a and b according to the rule division of the area-operators; resource group 2 includes resource nodes c, d, e; the resource group 3 contains resource nodes f, g.

Since there is a division of resource groups in the resource cluster, the number of resource nodes existing in different resource groups may be different, so that the average number of resource nodes in the resource group may be calculated, and thus the average number is used as a parameter used in a subsequent judging process.

Step 204, obtaining node information of resource nodes in the resource cluster under the condition that the resource scheduling environment information meets the preset scheduling condition.

In the embodiment of the application, the first resource node which receives the first resource acquisition request can firstly judge whether to perform 302 scheduling, and judge whether to perform 302 scheduling, then judge whether to perform 302 scheduling according to the resource scheduling environment information, and if the resource scheduling environment information meets the preset scheduling condition, then perform 302 scheduling, then acquire the node information of the resource node.

It should be noted that, the process of judging that the resource scheduling environment information meets the preset scheduling condition may be before acquiring the node information of the resource nodes in the resource cluster, or may be after acquiring the node information of the resource nodes in the resource cluster, which is not limited by the embodiment of the present application.

Optionally, in an embodiment of the present application, step 204 includes:

in sub-step 2041, node information of resource nodes in the resource cluster is obtained if the resource heat of the first resource acquisition request is less than or equal to a preset heat threshold, the update frequency is greater than or equal to a preset frequency threshold, and the average number is less than or equal to a preset average threshold.

In the embodiment of the application, when the resource heat of the first resource acquisition request is smaller than or equal to the preset heat threshold, the resource heat of the first resource acquisition request can be considered to be lower, and then 302 scheduling can be performed on the first resource acquisition request under the condition, because the flow of the resource data requested by the first resource acquisition request with lower resource heat is smaller, the first resource acquisition requests with smaller flow are uniformly concentrated on one 302 node to perform data source back, so that the 302 node can provide 302 scheduling to reduce the data source back cost on the basis of ensuring normal load pressure.

Optionally, in an embodiment of the present application, after step 203, the method may further include:

and step B11, executing the first resource acquisition request locally to send resource data to the terminal equipment under the condition that the resource heat of the first resource acquisition request is larger than a preset heat threshold.

For the resource heat of the first resource obtaining request being larger than the preset heat threshold, the first resource obtaining request with larger resource heat can be considered to have larger flow of the resource data requested by the first resource obtaining request with larger resource heat, the first resource obtaining requests with larger flow are uniformly concentrated on one 302 node to carry out data source returning, which can cause the load of the 302 node to be too high and influence the normal work of the 302 node,

therefore, the scheduling process of the 302 is not performed on the resource acquisition request with high resource heat, but the resource acquisition request is directly executed at the local of the resource node (such as the first resource node in fig. 1) which receives the resource acquisition request, so that the load pressure of the 302 node is reduced.

Optionally, after determining that the resource heat of the first resource obtaining request is less than or equal to the preset heat threshold, 302 scheduling may be performed, it needs to be further determined which 302 scheduling calculation policy is adopted, where the 302 scheduling calculation policy includes two modes, one mode is that the scheduling weight value of the online computing resource node in the embodiment of the present application is determined according to the scheduling weight value, the calculation policy of the target resource node serving as the 302 node is determined, and the other mode is that the hash ring is first built offline, and then the hash value of the first resource obtaining request is matched with the hash ring, so as to determine the mode of the 302 node.

In this step, the premise of selecting the first mode as the calculation policy for 302 scheduling is that the resource heat of the first resource acquisition request is less than or equal to the preset heat threshold, the update frequency is greater than or equal to the preset frequency threshold, and the average number is less than or equal to the preset average threshold, where the resource heat of the first resource acquisition request is less than or equal to the preset heat threshold, which indicates that the first resource acquisition request is a request for 302 scheduling. If the update frequency is greater than the preset frequency threshold, it indicates that there is a high-frequency update of the resource node in the current resource cluster scene, in this case, if the hash ring is built offline in the second mode, frequent hash ring reconstruction is required, for example, one hash ring is correspondingly reconstructed once per update, which results in a large ring building overhead, so the ring building overhead can be saved in the first mode. If the average number of the resource nodes in the resource group is smaller than or equal to the preset average threshold value, the number of the resource nodes contained in the resource group in the current resource cluster scene is smaller, in this case, if the method of offline construction of the hash ring in the method two is adopted, frequent reconstruction of the hash ring operation caused by frequent update of the resource group is also caused, and the ring construction cost is larger, so that the ring construction cost can be saved in the method one. And the premise of selecting the calculation strategy of the second scheduling mode 302 is that: first, the resource heat is less than or equal to a preset heat threshold and the update frequency is less than a preset frequency threshold; the second, the resource heat is less than or equal to the preset heat threshold and the average number is greater than the preset average threshold, either of which can be selected.

And 205, splicing the node name of the resource node with at least part of the information of the request information to obtain a splicing result.

Wherein the node information may include a node name of the resource node and an initial weight of the resource node.

In the embodiment of the application, corresponding node information is set for the resource node, the node information comprises the node name of the resource node and the initial weight of the resource node, the node name plays a role in marking the resource node, and the initial weight reflects the importance degree of the resource node.

The initial weight may be set in a scheduling policy synchronized by the scheduling policy maintenance end.

In the process of calculating the scheduling weight value of the resource node on line, the node name of the resource node is firstly required to be spliced with all or part of information of the resource acquisition request to obtain a splicing result, and the splicing result subsequently participates in hash calculation, so that the resource node has mathematical form representation, and the subsequent participation in decision calculation is more convenient.

For example, assume that the content information of the resource acquisition request is: http:// domain.com/app/stream. There are k resource nodes (stations) in the resource cluster: station_1, station_2..station_k, the resource node comprises a node name (station_i) and a weight (w) of the resource node, and for station_i, the corresponding splicing result s_i may be:

App/stream_i (partial information spliced with node name);

of course, the splicing result s_i corresponding to the station_i may also be:

http:// domain.com/app/stream station_i (all information spliced with node name).

And 206, performing hash calculation on the spliced result to obtain a first hash result of the resource node.

In the embodiment of the application, the splicing result is subjected to hash calculation to obtain the first hash result of the resource node, so that text information (content information of a resource acquisition request and node names of the resource node) associated with the resource node can be characterized in a mathematical form, and the text information is convenient to subsequently participate in calculation of a scheduling weight value.

Optionally, before step 201, the method further includes:

step B21, receiving resource node scheduling policy information;

and step B22, acquiring the node information according to the resource node scheduling policy information.

In the embodiment of the application, the scheduling policy maintenance terminal can synchronize scheduling policy information for each resource node, and the resource node can acquire node information from the scheduling policy information after receiving the scheduling policy information, wherein the node information comprises the identification of each resource node, the initial weight of the resource node and the like.

Step 207, calculating a scheduling weight value of the resource node according to the first hash result of the resource node, the initial weight of the resource node and the hash range set for the hash calculation.

Optionally, the scheduling weight value of the resource node is in positive correlation with the initial weight of the resource node.

In the embodiment of the application, the following formula 1 can be adopted to calculate the scheduling weight value of the resource node:

equation 1: si=wi/In (hash_max/xi);

In the embodiment of the application, the scheduling weight value reflects the probability that the resource node can be used as the target resource node, and the process of obtaining the scheduling weight value of the resource node through the formula 1 reflects the probability that the larger the initial weight is, the larger the resource node is selected as the target resource node. The judgment of whether the resource node can be selected as the target resource node by the scheduling weight value has the quantization of specific values

And step 208, using the resource node with the scheduling weight value larger than the scheduling weight value of other resource nodes as the target resource node.

In the embodiment of the application, according to the calculated scheduling weight value of each resource node, selecting the resource node with the node hash value larger than the node hash values of other resource nodes as a target resource node, and sending the communication information of the target resource node to the terminal equipment, thereby realizing 302 scheduling response, wherein the resource node with the scheduling weight value larger than the scheduling weight value of other resource nodes can be regarded as the node capable of realizing 302 scheduling response as the target resource node.

Step 209, generating a redirection response to the first resource acquisition request, and adding the communication information of the target resource node to the redirection response.

In the embodiment of the application, after the communication information of the target resource node is added to the response to the resource acquisition request, the subsequent terminal equipment can send a second resource acquisition request to the target resource node according to the communication information of the target resource node, the target resource node executes the second resource acquisition request, acquires the live broadcast resource from the data source and feeds the live broadcast resource back to the terminal equipment. Therefore, 302 scheduling is realized, so that data source return is realized, the whole process omits the process of constructing the hash ring and matching the hash ring in an off-line manner, and the expenditure for reconstructing the hash ring is greatly reduced under the scene of frequent updating of the resource cluster.

Optionally, step 208 may be specifically implemented by adding a preset redirection status code and communication information of the target resource node to a response to the resource acquisition request, where the status code is used to trigger the terminal device to send a second resource acquisition request to the target resource node.

And step 210, sending the redirection response to the terminal equipment.

In the embodiment of the present application, the preset redirection status code may be a (302) status code, and the terminal device agrees to trigger the operation of sending the second resource acquisition request to the target resource node when receiving (302) the status code. After receiving the second resource obtaining request, the target resource node processes the request, obtains resource data from the server where the data source is located, and returns the resource data to the terminal equipment.

a sub-step B31 of determining a second hash value of the first resource acquisition request according to the request information when the resource heat of the first resource acquisition request is less than or equal to a preset heat threshold, the update frequency is less than the preset frequency threshold, or the average number is greater than the preset average threshold;

Step B32, matching the second hash value with a pre-established hash ring to determine a target resource node; the hash ring comprises a plurality of hash values, the hash ring corresponds to the resource group, and the hash values on the hash ring correspond to resource nodes in the resource group.

In the embodiment of the present application, for the 302 scheduling performed in the second mode, one target resource node may be determined, and then a process of generating a redirection response for the first resource acquisition request based on the communication information of the target resource node is performed, for example, the communication information of the target resource node may be added to the 302 response for the first resource acquisition request, and then the communication information of the target resource node is returned to the terminal device.

In the embodiment of the present application, for steps B31-B32, the resource heat of the first resource acquisition request is less than or equal to the preset heat threshold, which indicates that the first resource acquisition request is a request that needs to be scheduled 302. And the update frequency is smaller than or equal to the preset frequency threshold, which indicates that the update frequency of the resource node existing in the current resource cluster scene is lower, in this case, the target resource node serving as the 302 node can be determined by adopting an offline hash ring construction and hash matching mode, and at this time, the cost for reconstructing the hash ring is lower due to the lower update frequency. If the average number of the resource nodes in the resource group is greater than the preset average threshold, the number of the resource nodes contained in the resource group in the current resource cluster scene is larger, and in this case, the ring building overhead is relatively smaller in a mode of offline construction of the hash ring in the mode II.

Therefore, when the resource heat of the first resource obtaining request is smaller than or equal to the preset heat threshold, but the update frequency is smaller than the preset frequency threshold or the average number is larger than the preset average threshold, the hash ring can be built offline first, then the hash value of the first resource obtaining request is matched with the hash ring, so that 302 scheduling is realized in a mode of determining 302 nodes, and on the basis of keeping less ring building cost, the query efficiency of the target resource nodes is improved through hash matching.

Specifically, a plurality of resource nodes can be selected to form a resource group according to actual service requirements, the resource group can exist in the resource group at the same time, one resource group can be regarded as one resource ring, one resource ring can be correspondingly constructed into one hash ring, the construction of the hash ring means that the resource nodes contained in the resource ring are respectively calculated into hash values and are organized into a virtual ring according to clockwise/anticlockwise directions, the hash values corresponding to the resource nodes can be distributed on the hash ring, so that one hash value on the hash ring corresponds to one resource node in the characterization resource ring, and the hash value corresponding to the resource node can be obtained by utilizing the node name of the resource node to perform hash calculation. After the hash ring is constructed, aiming at a first resource acquisition request sent by the terminal equipment, a second hash value of the first resource acquisition request can be obtained, and a target hash value matched with the second hash value on the hash ring is determined, so that a target resource node corresponding to the target hash value is determined as a target resource node, and the method for searching the target resource node through hash matching has high query efficiency.

Optionally, step B31 may specifically include:

sub-step B311, determining a mapping position of the second hash value on the hash ring;

sub-step B312 takes the hash value preceding or following the mapping position in the hash ring as the target hash value.

In the embodiment of the present application, for the implementation of the specific hash matching in the substep B311-B312, mapping the second hash value of the first resource acquisition request onto the hash ring, determining a specific mapping position, and then taking the previous (hash ring is constructed in a counterclockwise direction) or the next hash value (hash ring is constructed in a clockwise direction) of the mapping position in the hash ring as the target hash value.

For example, referring to FIG. 7, which shows a schematic diagram of a hash matching process, assume that there are four resource nodes in a resource group: after hash computation is performed on the resource node 1, the resource node 2, the resource node 3 and the resource node 4 according to the respective node names of the four resource nodes, four corresponding hash values can be obtained: the hash value 1 corresponding to the resource node 1, the hash value 2 corresponding to the resource node 2, the hash value 3 corresponding to the resource node 3 and the hash value 4 corresponding to the resource node 4 are distributed in the annular space according to the clockwise direction, so that the hash ring shown in fig. 7 can be obtained, after the hash ring corresponding to the resource group is constructed, the second hash value of the first resource acquisition request can be mapped onto the hash ring, the specific mapping position is determined, and then the resource node 2 corresponding to the next hash value 2 in the mapping position in the hash ring is used as the target resource node according to the clockwise arrangement mode in the hash ring, so that the rapid query of the target resource node is realized.

Optionally, after step 203, the method may further include:

and 212, calculating a node hash value of the resource node according to the node information of the resource node.

And 213, using the resource node with the node hash value larger than that of other resource nodes as the target resource node, and adding the communication information of the target resource node to the response to the resource acquisition request.

For steps 212-213, in another implementation manner, hash calculation may be performed according to node information of the resource node, so as to obtain a node hash value of the resource node, and a resource node with a node hash value greater than node hash values of other resource nodes is used as a target resource node, and communication information of the target resource node is added to a response to the resource acquisition request.

Referring to fig. 8, a flowchart illustrating specific steps of a live broadcast data processing method according to an embodiment of the present application includes:

step 301, receiving a first direct broadcast data acquisition request sent by a terminal device;

step 302, acquiring request information according to the first direct broadcast data acquisition request;

step 303, acquiring node information of live broadcast resource nodes in a live broadcast cluster;

step 304, determining a scheduling weight value of the live broadcast resource node according to the request information and the node information of the live broadcast resource node;

step 305, selecting a target live broadcast resource node with a scheduling weight value meeting a preset weight condition from the live broadcast resource node information;

step 306, generating a redirection response to the first resource acquisition request based on the communication information of the target live broadcast resource node;

step 307, sending the redirection response to the terminal equipment; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target live broadcast resource node based on the communication information of the target live broadcast resource node in the redirection response so as to acquire live broadcast data.

The principle of the embodiment of the present application is basically similar to that of the embodiment shown in fig. 5, except that the application in the live broadcast scenario is explicitly defined, the resource acquisition request is further defined for the live broadcast data acquisition request, the resource node is further defined for the live broadcast resource node, the resource data is further defined for the live broadcast data, and the specific implementation principle is not described in detail again with reference to the embodiment shown in fig. 5.

In the process of acquiring the request by the live broadcast resource node in the resource cluster, the scheduling weight value of the resource node can be calculated on line, the target live broadcast resource node is selected based on the scheduling weight value, the redirection response aiming at the first live broadcast resource acquisition request is generated based on the communication information of the target live broadcast resource node and returned to the terminal equipment, so that the terminal equipment sends a second live broadcast resource acquisition request to the target live broadcast resource node to acquire live broadcast data based on the target resource node, 302 scheduling is realized.

Referring to fig. 2, the embodiment of the present application further provides a request processing system in a live broadcast scenario, including: the system comprises terminal equipment and a live broadcast resource cluster, wherein the live broadcast resource cluster comprises a plurality of live broadcast resource nodes.

a second request receiving module 501, configured to receive a first direct broadcast data acquisition request sent by a terminal device;

a second request information obtaining module 502, configured to obtain request information according to the first direct broadcast data obtaining request;

a second node information obtaining module 503, configured to obtain node information of a live broadcast resource node in a live broadcast cluster;

a second scheduling determining module 504, configured to determine a scheduling weight value of the live broadcast resource node according to the request information and node information of the live broadcast resource node;

a live broadcast resource node selection module 505, configured to select, from the live broadcast resource node information, a target live broadcast resource node whose scheduling weight value satisfies a preset weight condition;

a second response generating module 506, configured to generate a redirect response for the first resource acquisition request based on the communication information of the target live broadcast resource node;

a second response sending module 507, configured to send the redirection response to the terminal device; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target live broadcast resource node based on the communication information of the target live broadcast resource node in the redirection response so as to acquire live broadcast data.

The terminal device is used for: transmitting a live broadcast data acquisition request to a first live broadcast resource node in a live broadcast resource cluster; and sending a second resource acquisition request to the target live broadcast resource node according to the communication information of the target live broadcast resource node in the redirection response sent by the first live broadcast resource node;

In the embodiment of the application, the target live broadcast resource node acquires corresponding live broadcast data from the data source and feeds the corresponding live broadcast data back to the terminal equipment through 302 scheduling, so that the effect of reducing the cost of the data back source can be realized, in addition, the whole 302 scheduling process is used for calculating the scheduling weight value of the live broadcast resource node on line, selecting the target live broadcast resource node based on the scheduling weight value, adding the communication information of the target live broadcast resource node into the response aiming at the resource acquisition request so that the terminal equipment can send a second resource acquisition request to the target live broadcast resource node, thereby omitting the offline construction of hash ring and hash ring matching in 302 scheduling, and greatly reducing the cost of reconstructing the hash ring under the scene of frequent updating of the resource cluster.

In summary, in the embodiment of the present application, in the process of processing a proxy processing request that satisfies the 302 scheduling policy, the scheduling weight value of the resource node is calculated online, and the target live broadcast resource node is selected based on the scheduling weight value, and the communication information of the target live broadcast resource node is added to the response to the first live broadcast data acquisition request, so that the terminal device sends the second live broadcast data acquisition request to the target live broadcast resource node, thereby implementing 302 scheduling.

Referring to fig. 9, a block diagram of a request processing apparatus according to an embodiment of the present application is shown, including:

a first request receiving module 401, configured to receive a first resource acquisition request sent by a terminal device;

a first request information obtaining module 402, configured to obtain request information according to the first resource obtaining request;

A first node information obtaining module 403, configured to obtain node information of resource nodes in a resource cluster;

a first scheduling determining module 404, configured to determine a scheduling weight value of the resource node according to the request information of the first resource acquisition request and the node information of the resource node;

a first node selection module 405, configured to select, from the resource node information, a target resource node whose scheduling weight value meets a preset weight condition;

a first response generation module 406, configured to generate a redirect response for the first resource acquisition request based on the communication information of the target resource node;

a first response sending module 407, configured to send the redirection response to the terminal device; the redirection response is used for the terminal equipment to send a second resource acquisition request to the target resource node based on the communication information of the target resource node in the redirection response so as to acquire resource data.

Optionally, the node information includes a node name of the resource node and an initial weight of the resource node;

the first schedule determining module 404 includes:

the splicing sub-module is used for splicing the node name of the resource node with at least part of the information of the request information to obtain a splicing result;

The first computing sub-module is used for carrying out hash computation on the splicing result to obtain a first hash result of the resource node;

and the second computing sub-module is used for computing the scheduling weight value of the resource node according to the first hash result of the resource node, the initial weight of the resource node and the hash range set for the hash computation.

Optionally, the method further comprises:

the scheduling policy receiving module is used for receiving the scheduling policy information of the resource nodes;

and the third node information acquisition module is used for acquiring the node information according to the resource node scheduling policy information.

Optionally, the first response generation module 406 includes:

a selecting sub-module, configured to use the resource node with the scheduling weight value greater than the scheduling weight values of other resource nodes as the target resource node;

and the adding sub-module is used for generating a redirection response aiming at the first resource acquisition request and adding the communication information of the target resource node into the redirection response.

Optionally, the method further comprises:

The scheduling environment information acquisition module is used for acquiring resource scheduling environment information;

the first node information obtaining module 403 is further configured to obtain node information of a resource node in a resource cluster when it is determined that the resource scheduling environment information meets a preset scheduling condition.

Optionally, the resource scheduling context information includes: the first node information obtaining module 403 is further configured to obtain node information of a resource node in the resource cluster when the resource heat of the resource obtaining request is less than or equal to a preset heat threshold, the update frequency is greater than or equal to a preset frequency threshold, and the average number of the resource nodes in the resource cluster is less than or equal to a preset average threshold, where the resource heat of the resource data corresponding to the first resource obtaining request, the update frequency of the resource cluster, and the average number of the resource nodes in the resource cluster are equal to or less than a preset average threshold.

Optionally, the apparatus further comprises:

and the local processing submodule is used for executing the first resource acquisition request locally to send resource data to the terminal equipment under the condition that the resource heat of the first resource acquisition request is larger than a preset heat threshold.

Optionally, the apparatus further comprises:

a first hash module, configured to determine, according to the request information, a second hash value of the first resource acquisition request when the resource heat of the first resource acquisition request is less than or equal to a preset heat threshold, and the update frequency is less than the preset frequency threshold or the average number is greater than the preset average threshold;

the query module is used for matching the second hash value with a pre-established hash ring and determining a target resource node; the hash ring comprises a plurality of hash values, the hash ring corresponds to the resource group, and the hash values on the hash ring correspond to resource nodes in the resource group.

Optionally, the query module includes:

a mapping sub-module, configured to determine a mapping position of the second hash value on the hash ring;

and the determining submodule is used for taking a previous hash value or a next hash value of the mapping position in the hash ring as the target hash value.

Optionally, the apparatus further comprises:

the second hash module is used for calculating a node hash value of the resource node according to the node information of the resource node;

and the screening hash module is used for taking the resource node with the node hash value larger than that of other resource nodes as the target resource node, and adding the communication information of the target resource node to the response to the resource acquisition request.

Optionally, the first response generation module 406 includes:

and the processing sub-module is used for adding a preset status code and the communication information of the target resource node into the response to the resource acquisition request, wherein the status code is used for triggering the terminal equipment to send a second resource acquisition request to the target resource node.

The embodiment of the application also provides a non-volatile readable storage medium, in which one or more modules (programs) are stored, where the one or more modules are applied to a device, and the device can execute instructions (instructions) of each method step in the embodiment of the application.

Embodiments of the application provide one or more machine-readable media having instructions stored thereon that, when executed by one or more processors, cause an electronic device to perform a method as described in one or more of the above embodiments. In the embodiment of the application, the electronic equipment comprises various types of equipment such as terminal equipment, a server (cluster) and the like.

Embodiments of the present disclosure may be implemented as an apparatus for performing a desired configuration using any suitable hardware, firmware, software, or any combination thereof, which may include electronic devices such as terminal devices, servers (clusters), etc. Fig. 10 schematically illustrates an exemplary apparatus 1000 that may be used to implement various embodiments described in embodiments of the present application.

For one embodiment, fig. 10 illustrates an example apparatus 1000 having one or more processors 1002, a control module (chipset) 1004 coupled to at least one of the processor(s) 1002, a memory 1006 coupled to the control module 1004, a non-volatile memory (NVM)/storage 1008 coupled to the control module 1004, one or more input/output devices 1010 coupled to the control module 1004, and a network interface 1012 coupled to the control module 1004.

The processor 1002 may include one or more single-core or multi-core processors, and the processor 1002 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 1000 may be used as a terminal device, a server (a cluster), or the like in the embodiments of the present application.

In some embodiments, the apparatus 1000 can include one or more computer-readable media (e.g., memory 1006 or NVM/storage 1008) having instructions 1014 and one or more processors 1002 in combination with the one or more computer-readable media configured to execute the instructions 1014 to implement the modules to perform the actions described in this disclosure.

For one embodiment, the control module 1004 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 1002 and/or any suitable device or component in communication with the control module 1004.

The control module 1004 may include a memory controller module to provide an interface to the memory 1006. The memory controller modules may be hardware modules, software modules, and/or firmware modules.

Memory 1006 may be used to load and store data and/or instructions 1014 for device 1000, for example. For one embodiment, the memory 1006 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the memory 1006 may comprise a double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).

For one embodiment, the control module 1004 may include one or more input/output controllers to provide an interface to the NVM/storage 1008 and the input/output device(s) 1010.

For example, NVM/storage 1008 may be used to store data and/or instructions 1014. NVM/storage 1008 may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).

NVM/storage 1008 may include storage resources that are physically part of the device on which apparatus 1000 is installed, or may be accessible by the device without necessarily being part of the device. For example, NVM/storage 1008 may be accessed over a network via input/output device(s) 1010.

Input/output device(s) 1010 may provide an interface for apparatus 1000 to communicate with any other suitable device, input/output device 1010 may include communication components, audio components, sensor components, and the like. Network interface 1012 may provide an interface for device 1000 to communicate over one or more networks, and device 1000 may communicate wirelessly with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols, such as accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.

For one embodiment, at least one of the processor(s) 1002 may be packaged together with logic of one or more controllers (e.g., memory controller modules) of the control module 1004. For one embodiment, at least one of the processor(s) 1002 may be packaged together with logic of one or more controllers of the control module 1004 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 1002 may be integrated on the same mold as logic of one or more controllers of the control module 1004. For one embodiment, at least one of the processor(s) 1002 may be integrated on the same die with logic of one or more controllers of the control module 1004 to form a system on chip (SoC).

In various embodiments, the apparatus 1000 may be, but is not limited to being: a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.), among other terminal devices. In various embodiments, device 1000 may have more or fewer components and/or different architectures. For example, in some embodiments, the apparatus 1000 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and a speaker.

The detection device can adopt a main control chip as a processor or a control module, sensor data, position information and the like are stored in a memory or an NVM/storage device, a sensor group can be used as an input/output device, and a communication interface can comprise a network interface.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

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

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

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

While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the application.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

The foregoing has described in detail the method and apparatus for processing a request, the request processing system in live broadcast scenario, the electronic device and the machine readable medium, and specific examples have been applied to illustrate the principles and embodiments of the present application, and the above description of the embodiments is only for helping to understand the method and core idea of the present application; in the same way, the person skilled in the art, based on the idea of the present application, may change the specific embodiments and the application scope, and in summary, the present disclosure should not be interpreted as limiting the present application.

Claims

1. A method of processing a request, comprising: receiving a first resource acquisition request sent by terminal equipment;

acquiring node information of resource nodes in a resource cluster;

2. The method of claim 1, wherein the node information includes a node name of the resource node and an initial weight of the resource node;

the determining the scheduling weight value of the resource node according to the request information and the node information of the resource node includes:

splicing the node name of the resource node with at least part of the information of the request information to obtain a splicing result;

performing hash calculation on the splicing result to obtain a first hash result of the resource node;

and calculating a scheduling weight value of the resource node according to the first hash result of the resource node, the initial weight of the resource node and the hash range set for the hash calculation.

3. The method as recited in claim 2, further comprising:

receiving scheduling policy information of a resource node;

And acquiring the node information according to the resource node scheduling policy information.

4. The method of claim 1, wherein the generating a redirect response for the first resource acquisition request based on the communication information of the target resource node comprises:

taking the resource node with the scheduling weight value larger than the scheduling weight values of other resource nodes as the target resource node;

a redirect response to the first resource acquisition request is generated and the communication information of the target resource node is added to the redirect response.

5. The method as recited in claim 1, further comprising:

acquiring resource scheduling environment information;

the obtaining node information of the resource nodes in the resource cluster includes:

and under the condition that the resource scheduling environment information meets the preset scheduling condition, acquiring node information of resource nodes in the resource cluster.

6. The method of claim 5, wherein the resource scheduling context information comprises: at least one of resource heat of resource data corresponding to the first resource obtaining request, update frequency of the resource cluster and average number of resource nodes in a resource group; wherein the resource group is composed of at least one resource node in the resource cluster.

7. The method of claim 5, wherein scheduling context information at the resource comprises: under the conditions that the resource heat of the resource data corresponding to the first resource obtaining request, the update frequency of the resource cluster and the average number of the resource nodes in the resource group are determined, obtaining the node information of the resource nodes in the resource cluster under the condition that the resource scheduling environment information meets the preset scheduling condition comprises:

and acquiring node information of the resource nodes in the resource cluster under the condition that the resource heat of the resource acquisition request is smaller than or equal to a preset heat threshold, the updating frequency is larger than or equal to a preset frequency threshold and the average number is smaller than or equal to a preset average threshold.

8. The method of claim 7, wherein the method further comprises:

and under the condition that the resource heat of the first resource acquisition request is larger than a preset heat threshold, executing the first resource acquisition request locally to send resource data to the terminal equipment.

9. The method of claim 7, wherein the method further comprises:

determining a second hash value of the first resource acquisition request according to the request information when the resource heat of the first resource acquisition request is smaller than or equal to a preset heat threshold, and the update frequency is smaller than the preset frequency threshold or the average number is larger than the preset average threshold;

Matching the second hash value with a pre-established hash ring to determine a target resource node; the hash ring comprises a plurality of hash values, the hash ring corresponds to the resource group, and the hash values on the hash ring correspond to resource nodes in the resource group.

10. A live data processing method, comprising:

11. A request processing apparatus, comprising:

12. A live data processing system, comprising:

a live broadcast resource cluster, wherein the live broadcast resource cluster comprises a plurality of live broadcast resource nodes;

the second request receiving module is used for receiving a first direct broadcast data acquisition request sent by the terminal equipment;

13. An electronic device, comprising:

a processor; and

a memory having executable code stored thereon that, when executed, causes the processor to perform the method of any of claims 1 to 10.

14. One or more machine readable media having executable code stored thereon that, when executed, causes a processor to perform the method of any of claims 1 to 10.