CN118612223A - Data processing method, device, system, computer equipment and storage medium - Google Patents

Abstract

The present application relates to a data processing method, device, system, computer equipment, storage medium and computer program product. The method comprises: the original server receives a first data request message sent by a terminal, and redirects the first data request message to a first migration server; the first migration server feeds back a first response message to the terminal; the original server receives a second data request message sent by the terminal, and redirects the second data request message to the first migration server; the first migration server sends a migration request to a second migration server that meets the message response condition when the first migration server meets the message migration condition, and sends redirection information to the original server for instructing the original server to redirect the message sent by the terminal to the second migration server when receiving confirmation information fed back by the second migration server based on the migration request. The above method can improve data processing efficiency.

Description

Data processing method, device, system, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technology, and in particular to a data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product.

Background Art

With the rapid development of computer technology, server clusters consisting of multiple servers have emerged. Terminals can establish connections with servers in the server cluster to obtain the required data resources. The server connected to the terminal is called the original server. If the original server cannot feedback the corresponding data resources, the data request can be migrated to another server in the server cluster, and the other server responds to the user's needs.

In traditional technology, if request migration is required, the original server selects the migration server. If multiple requests need to be migrated, the response speed of user needs will be heavily dependent on the performance of the original server, resulting in low data processing efficiency.

Summary of the invention

Based on this, it is necessary to provide a data processing method, apparatus, system, computer equipment, computer-readable storage medium and computer program product that can improve data processing efficiency in response to the above technical problems.

In a first aspect, the present application provides a data processing method, which is applied to a first migration server, and the method includes:

In response to the first data request message carried in the first redirection message sent by the original server, a first response message is fed back to the terminal that sent the first data request message;

receiving a second redirection message including a second data request message sent by the original server; the second data request message is sent by the terminal to the original server when the first response message is received;

If the first migration server meets the message migration condition, sending a migration request for the second data request message to a second migration server that meets the message response condition;

When receiving confirmation information fed back by the second migration server based on the migration request, redirection information is sent to the original server; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server.

In a second aspect, the present application provides a data processing method, which is applied to an original server, and the method includes:

receiving a first data request message sent by a terminal, and sending a first redirect message including the first data request message to a first migration server;

receiving a second data request message sent by the terminal; the second data request message is sent by the terminal when the first response message is received; the first response message is fed back to the terminal by the first migration server based on the first data request message;

Sending a second redirection message including the second data request message to the first migration server;

When the first migration server meets the message migration condition, it receives redirection information for the second data request message; the redirection information is sent by the first migration server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server; the second migration server meets the message response condition.

In a third aspect, the present application further provides a data processing system, the system comprising an original server, a first migration server, and a second migration server;

The original server receives a first data request message sent by the terminal, and sends a first redirect message including the first data request message to the first migration server;

The first migration server feeds back a first response message to the first data request message to the terminal;

The original server receives the second data request message sent by the terminal, and sends a second redirect message including the second data request message to the first migration server; the second data request message is sent by the terminal when receiving the first response message;

When the first migration server satisfies the message migration condition, the first migration server sends a migration request for the second data request message to a second migration server that satisfies the message response condition;

The first migration server sends redirection information to the original server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server.

In a fourth aspect, the present application further provides a data processing device, applied to a first migration server, the device comprising:

A response message feedback module, used to respond to the first data request message carried in the first redirection message sent by the original server, and feed back a first response message to the terminal that sent the first data request message;

a redirection message receiving module, configured to receive a second redirection message including a second data request message sent by the original server; the second data request message is sent by the terminal to the original server when the terminal receives the first response message;

a migration module, configured to send a migration request for the second data request message to a second migration server that meets a message response condition if the first migration server meets a message migration condition;

The redirection information sending module is used to send redirection information to the original server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server.

In a fifth aspect, the present application further provides a data processing device, applied to an original server, the device comprising:

A data request message receiving module, used for receiving a first data request message sent by a terminal;

A redirection message sending module, configured to send a first redirection message including the first data request message to a first migration server;

The data request message receiving module is further configured to receive a second data request message sent by the terminal; the second data request message is sent by the terminal after receiving the first response message; the first response message is fed back to the terminal by the first migration server based on the first data request message;

The redirection message sending module is further configured to send a second redirection message including the second data request message to the first migration server;

A redirection information receiving module is used to receive redirection information for the second data request message when the first migration server meets the message migration condition; the redirection information is sent by the first migration server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server; the second migration server meets the message response condition.

In a sixth aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

In a seventh aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the steps of the above method when executed by a processor.

In an eighth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

In the above-mentioned data processing method, system, apparatus, computer equipment, computer-readable storage medium and computer program product, the original server receives a first data request message sent by a terminal, and sends a first redirection message containing the first data request message to a first migration server; the first migration server feeds back a first response message to the first data request message to the terminal; the original server receives a second data request message sent by the terminal, and sends a second redirection message containing the second data request message to the first migration server; the first migration server sends a migration request for the second data request message to a second migration server that meets the message response conditions when the first migration server meets the message migration conditions; the first migration server sends redirection information to the original server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server. During the above data processing process, the first migration server that responded to the previous data request message determines the second migration server that responds to the current data request message, and negotiates with the second migration server by sending a migration request. After obtaining confirmation information fed back by the second migration server, the relocation information is sent to the original server to instruct the original server to redirect the message sent by the terminal to the second migration server. Compared with the traditional technology of centralized migration processing by the original server, this is equivalent to a distributed migration processing method, which can reduce the time loss of multiple migration processes and is conducive to improving data processing efficiency.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is an application environment diagram of a data processing method in one embodiment;

FIG2 is a schematic diagram of a data processing interaction process in one embodiment;

FIG3 is a schematic flow chart of a data processing method in one embodiment;

FIG4 is a schematic diagram of a redirection process in one embodiment;

FIG5 is a schematic diagram of the interaction process between the content scheduling center and the server in one embodiment;

FIG6 is a schematic diagram of content scheduling information in one embodiment;

FIG7 is a schematic diagram of a migration negotiation process in one embodiment;

FIG8 is a schematic flow chart of a data processing method in another embodiment;

FIG9 is a schematic diagram of a data processing interaction process in another embodiment;

FIG10 is a schematic diagram of a migration method based on dual-end negotiation in one embodiment;

FIG11 is a schematic diagram of a single-end migration mode of a server in one embodiment;

FIG12 is a schematic flow chart of a data processing method in yet another embodiment;

FIG13 is a block diagram of a data processing device in one embodiment;

FIG14 is a block diagram of a data processing device in another embodiment;

FIG. 15 is a diagram showing the internal structure of a computer device in one embodiment.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

The data processing method provided in the embodiment of the present application can be applied in the application environment as shown in Figure 1. Among them, the terminal 110 can communicate with the server cluster 120 through a network. The communication network can be a wired network or a wireless network. Therefore, the terminal 110 and the server cluster 120 can be directly or indirectly connected through wired or wireless communication. For example, the terminal 110 can be indirectly connected to the server cluster 120 through a wireless access point, or the terminal 110 can be directly connected to the server cluster 120 through a wide area network (WAN), and the present application does not limit this. The wide area network can be, for example, the Internet.

Among them, the terminal 110 can be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The embodiment of the present application can be applied to multimedia data processing scenarios, and the data can be, for example, video or audio. A client related to data acquisition or data browsing can be installed on the terminal 110, and the client can be software (such as a browser, video software, etc.), or a web page, a small program, etc. The server cluster 120 is a background server corresponding to software or a web page, a small program, etc., or a server dedicated to data distribution services. Further, the server cluster 120 can be a server cluster or a distributed system composed of multiple physical servers, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network, content distribution network), and basic cloud computing services such as big data and artificial intelligence platforms.

Cloud technology refers to a hosting technology that unifies hardware, software, network and other resources in a wide area network or local area network to achieve data computing, storage, processing and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model. It can form a resource pool, which is used on demand and flexible and convenient. Cloud computing technology will become an important support. The background services of technical network systems require a large amount of computing and storage resources, such as video websites, picture websites and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark, and all need to be transmitted to the background system for logical processing. Data of different levels will be processed separately. All kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

It can be understood that in the application scenario of the present application, the number of terminals 110 can be multiple, that is, the server cluster 120 can respond to data requests from multiple terminals 110, and each terminal can establish a network connection with each server in the server cluster 120 so that data can be exchanged between the terminal and the server.

Further, the server cluster 120 may include an original server 121, a first migration server 122, and a second migration server 123. The original server 121 is the object of the request message of the terminal 110, that is, the terminal 110 obtains data resources by sending a data request message to the original server 121. It can be understood that during the interaction between the terminal 110 and the server cluster 120, the terminal 110 does not perceive the request migration, but always obtains data resources by sending a request message to the original server 121. In a specific implementation, the original server 121 can be the response server of the first data request message sent by the terminal 110, that is, after the terminal 110 sends the first data request message to the server cluster 120, the data request message will be distributed to the server (that is, the original server 121) with response capability in the server cluster 120 for processing, and the terminal 110 obtains the response message fed back by the original server 121. After that, the terminal 110 can initiate a new data request to the server cluster 120 by interacting with the original server 121. If the original server 121 can feedback the data resources requested by the new data request, the original server 121 will continue to respond to the user's needs. If the original server 121 cannot feedback the data resources requested by the new data request, the data request can be migrated to another server in the server cluster 120, and the other server will respond to the user's needs.

As shown in FIG. 2 , the present application is directed to a data processing scenario in which at least two migration requests occur, wherein the solid line represents the interaction process of the first migration request, and the dotted line represents the interaction process of the second migration request. Specifically, the original server 121 receives a first data request message ① sent by the terminal 110, and sends a first redirection message ② containing the first data request message ① to the first migration server 122; the first migration server 122 feeds back a first response message ③ of the first data request message ① to the terminal 110; upon receiving the first response message ③, the terminal 110 may send a second data request message ④ to the original server 121; the original server 121 sends a second redirection message ⑤ containing the second data request message ④ to the first migration server 122; the first migration server 122, when satisfying the message migration condition, sends a migration request ⑥ for the second data request message ④ to the second migration server 123 that satisfies the message response condition, and upon receiving confirmation information ⑦ fed back by the second migration server 123 based on the migration request ⑥, sends redirection information ⑧ to the original server 121; the redirection information ⑧ is used to instruct the original server 121 to redirect the message sent by the terminal 110 to the second migration server 123. It can be understood that the second response message ⑨ of the second data request message ④ will be fed back to the terminal 110 by the second migration server 123. At this point, the message sent by the terminal 110 to the original server 121 will be migrated to the second migration server 123 through redirection, and will no longer be migrated to the first migration server 122. If a subsequent migration request is required, the second migration server 123 can serve as a new first migration server to complete the migration by executing the above data processing logic.

It should be understood that although the terms first, second, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, a first data request message may also be referred to as a second data request message, and similarly, a second data request message may also be referred to as a first data request message.

That is to say, by adopting the scheme of the present application, when faced with multiple data requests and involving multiple requests for migration, the first migration server that responded to the previous data request message determines the second migration server that responds to the current data request message, and negotiates with the second migration server by sending a migration request. When the confirmation information fed back by the second migration server is obtained, the relocation information is sent to the original server to instruct the original server to redirect the message sent by the terminal to the second migration server. This can realize distributed migration processing, thereby reducing the time loss of multiple migration processes, which is conducive to improving data processing efficiency, and then being able to more quickly feedback the requested data resources to the terminal, thereby improving the networking capabilities of the server cluster and the business experience of the terminal.

In one embodiment, as shown in FIG3 , a data processing method is provided. The method may be executed by a computer device, which may be the first migration server shown in FIG1 , and includes the following steps:

Step S302: In response to the first data request message carried in the first redirection message sent by the original server, a first response message is fed back to the terminal that sent the first data request message.

Among them, the original server is the message sending object of the terminal. That is, for the terminal, it will not perceive the request migration, but always send messages to the original server to realize the interaction between the terminal and the server cluster. In a specific implementation, the original server can be the response server of the first data request message sent by the terminal, that is, after the terminal sends the first data request message to the server cluster, the data request message will be distributed to the server with response capability in the server cluster (that is, the original server) for processing, and the terminal obtains the response message fed back by the original server. After that, the terminal can initiate a new data request to the server cluster by interacting with the original server. If the original server can feedback the data resources requested by the new data request, the original server will continue to respond to the user's needs. If the original server cannot feedback the data resources requested by the new data request, the data request can be migrated to another server in the server cluster, and the other server will respond to the user's needs.

A data request message refers to a message sent by a terminal to an original server to request data resources. The data request message can be obtained by encapsulating a data request based on a communication protocol, and the communication protocol may include, for example, the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), or the Quick UDP Internet Connection (QUIC). A redirect message is a message information obtained after the original message is redirected. That is, the redirect message carries the original message being redirected.

In a specific embodiment, the redirection operation of the message can be implemented by a redirector in the server. The redirector can specifically operate on the original message based on the five-tuple information of the message (recorded as five_tuple), wherein the five-tuple is the five basic attributes of a network data packet, including source address (src), destination address (dst), source port (sport), destination port (dport) and protocol type (ptl_type). In network communication, each data packet contains these five attributes, which together constitute the unique identifier of the data packet. Further, the operation on the original message may include dropping (drop), receiving (receive) and redirecting (redirect). "Receive" means that the server can meet the needs of the message sender and feedback the corresponding response message, and "redirect" means that the server cannot meet the needs of the message sender and needs to redirect the message to other servers for processing. It can be understood that the five-tuple information of the message can characterize the data flow direction of the message, and then characterize the connection between the two interacting parties. Take the data request message sent by the terminal to the original server as an example. The source address of the data request message is the terminal address, the destination address is the original server address, the source port is the port number of the terminal, the destination port is the port number of the original server, and the protocol type is the communication protocol type. Among them, the port number and the communication protocol type need to be negotiated and determined by both parties before the terminal sends the first message to the original server.

Optionally, the redirector can operate on the original message based on the configuration table shown in the following table. The five-tuple information can represent the connection between the server where the redirector is located and other devices. Taking the connection between the original server and the terminal as an example, each five-tuple information can represent the connection between the original server and different terminals.

A response message refers to message information fed back to meet the needs of the message sender. Specifically for the present application, the response message of the data request message carries the data resources requested by the data request message. The data resources may include at least one of video, audio or text. Similar to the data request message, the response message may also be obtained by encapsulating the data request based on the communication protocol. In practical applications, the communication protocols of the data request message and the response message may be the same, so that the interacting parties do not need to negotiate the communication protocol multiple times.

Specifically, the terminal may send a first data request message to the original server, in which the resource identifier of the data resource requested by the terminal is carried. The resource identifier refers to identification information that can uniquely characterize the data resource. The resource identifier may be, for example, a resource storage address or a URI (Uniform Resource Identifier). The original server may determine whether it is necessary to migrate the request to another server according to actual conditions. If migration is not required, the first response message corresponding to the first data request message is fed back to the terminal. It can be understood that the first response message carries the data resource requested by the first data request message. If migration is required, the original server may determine the migration object of the first data request message from the server cluster, record it as the first migration server, and send a first redirect message carrying the first data request message to the first migration server. Thus, the first migration server may respond to the first data request message and feed back the first response message to the terminal.

There is no single way to determine whether a requested migration is necessary.

In a specific embodiment, the original server can extract the resource identifier from the first data request message, and determine whether to request migration based on the resource identifier. Specifically, if the original server can obtain the data resource represented by the resource identifier locally, migration is not performed; if the original server cannot obtain the data resource represented by the resource identifier locally, migration is required.

In a specific embodiment, the original server may also determine whether request migration is required in combination with the resource identifier and the current load information. The load information may include, for example, CPU (Central Processing Unit) utilization, memory usage, traffic size, etc. For example, if the original server can locally obtain the data resource represented by the resource identifier, and the current load is relatively low and can meet the message response requirements, then migration is not performed. If the original server cannot locally obtain the data resource represented by the resource identifier, and/or the current load is relatively high so that the message response requirements cannot be met, then migration is required.

In a specific embodiment, the data processing method further includes: obtaining a confirmation message fed back by the terminal based on the first response message; and when it is determined based on the confirmation message that packet loss occurs in the first response message, performing a packet loss repair operation on the first response message.

Among them, the confirmation message is received by the original server from the terminal and redirected to the first migration server. Specifically, after receiving the first response message, the terminal can feed back a confirmation message to the original server to declare the message information received or not received by the terminal. The confirmation message is redirected to the first migration server by the original server according to the redirection rule, so that the first migration server can judge whether the first response message has a packet loss phenomenon based on the message information received or not received by the terminal. If the message information declared received by the terminal is inconsistent with the message information actually sent by the first migration server through the first response message, or the terminal declares that all the requested data resources have not been received, the first migration server determines that there is a packet loss phenomenon, performs a packet loss repair operation for the first response message, and retransmits the lost message.

In this embodiment, packet loss is determined based on the confirmation message fed back by the terminal, and packet loss repair is performed when packet loss occurs, which can ensure that the server can provide the data resources required by the terminal and improve the data processing effect.

Step S304: Receive a second redirection message including a second data request message sent by the original server.

The second data request message is sent by the terminal to the original server when the terminal receives the first response message. The second data request message is a new data request message different from the first data request message. It can be understood that during the interaction between the same terminal and the server cluster, new data requirements may be generated as the interaction progresses. Therefore, when the terminal receives the first response message corresponding to the first data request message, it can send a second data request message to the original server to request new data resources.

As described above, the original server can determine the operation for the message based on the five-tuple information of the message. The five-tuple information of the second data request message is the same as the five-tuple information of the first data request message. In the case where the first data request message is redirected to the first migration server, the operation corresponding to the five-tuple information is redirection, so the original server will encapsulate the second data request message into a second redirection message according to the same redirection rule as the first data request message, and send it to the first migration server. In this case, the first migration server can receive the second redirection message containing the second data request message sent by the original server.

Exemplarily, as shown in FIG4 , the terminal may send a second data request message (Pkt_req) to the original server, in which the first data request message carries the resource identifier of the data resource requested by the terminal. The original server will encapsulate the second data request message into a second redirect message (Pkt_req_redirect) according to the same redirection rule as the first data request message, and send it to the first migration server. After the first migration server obtains the second redirect message, it identifies the new data request and determines whether migration is required.

Step S306: If the first migration server meets the message migration condition, the first migration server sends a migration request for the second data request message to the second migration server that meets the message response condition.

Among them, the first migration server satisfies the message migration condition, which may mean that the first migration server cannot obtain the data resources requested by the second data request message locally, or it may mean that the current load of the first migration server is so high that it cannot meet the message response requirements of the second data request message. The message response condition and the message migration condition may be mutually exclusive. That is, the second migration server satisfies the message response condition, which may mean that the second migration server can obtain the data resources requested by the second data request message locally, or it may mean that the second migration server can obtain the data resources requested by the second data request message locally, and the current load of the first migration server is low, which can meet the message response requirements of the second data request message.

The migration request is used for the first migration server and the second migration server to negotiate the migration operation of the second data request message, that is, the migration request carries the associated information of the second data request message. The associated information may include connection status information and application status information. The connection status information includes but is not limited to the terminal information of the terminal, the server information of the original server, the protocol type, the transport layer status information of the first migration server and the terminal, the message number, etc. The terminal information and the server information may include the IP address, the port number, etc. The transport layer status information of the first migration server may include the sending window value, the amount of data in transit, etc., and the transport layer status information of the terminal may include the receiving window value, the effective available bandwidth, etc. The application status information may include the resource identifier of the data resource requested by the second data request message, and may also include the key for encrypting and decrypting the user data.

Specifically, when the first migration server receives the second redirection message, it can determine whether it meets the message migration condition according to the second data request message included in the second redirection message. If so, it determines a second migration server that meets the message response condition of the first data request message from each server in the server cluster, and sends a migration request for the second data request message to the second migration server.

Furthermore, the first migration server can determine the second migration server that meets the message response condition of the first data request message by obtaining the load information of each server in the server cluster and the resource identifier of the data resources that each server can provide; the first migration server can also directly obtain the server identifier of the second migration server that meets the message response condition of the first data request message, and then send a migration request for the second data request message to the second migration server. The server identifier can be determined by the content scheduling center in the server cluster.

The content scheduling center may be a separate server or may be located inside each server. In particular, as shown in Figure 5, the content scheduling center may periodically synchronize its own content scheduling information for selecting a migration server to each server in the server cluster. As shown in Figure 6, the content scheduling information may include, for example, a resource identifier, and server information and load information of a server that can read the data resource represented by the resource identifier.

Step S308: upon receiving confirmation information fed back by the second migration server based on the migration request, redirection information is sent to the original server.

The redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server. The terminal refers to the initiator of the second data request message. The message sent by the terminal may include all messages sent by the terminal to the original server after the original server receives the redirection information, and may specifically include data request messages, data confirmation messages, etc.

Specifically, when receiving a migration request for the second data request message, the second migration server may agree to the migration or not. When agreeing to migrate, the second migration server may send confirmation information to the first migration server based on the migration request, so that the first migration server may send redirection information for the message received from the terminal to the original server when receiving the confirmation information, so that the original server may redirect the message sent by the terminal to the second migration server later. Furthermore, when the second migration server migrates, it may feed back a second response message to the second data request message to the terminal, and the second response message carries the data resources requested by the second data request message.

In a specific embodiment, the data processing method further includes: upon receiving confirmation information fed back by the second migration server based on the migration request, sending a response start notification to the second migration server.

Among them, the response start notification is used to instruct the second migration server to feed back a second response message to the second data request message to the terminal. Specifically, as shown in FIG7 , when the first migration server meets the message migration conditions and determines that migration is required, it negotiates migration with the second migration server. The first migration server can send a migration request (Pkt_mig_req) for the second data request message to the second migration server. When receiving a negotiation confirmation message (Pkt_mig_ack) fed back by the second migration server based on the migration request, and the negotiation confirmation message carries confirmation information that supports migration, the first migration server sends a redirection rule update instruction carrying redirection information to the original server on the one hand, to instruct the original server to redirect subsequent messages sent by the terminal to the second migration server; on the other hand, the first migration server sends a response start notification to the second migration server to notify the second migration server to feed back a second response message to the second data request message to the terminal.

In this embodiment, by sending a response start notification to the second migration server to instruct the second migration server to feed back a second response message to the second data request message to the terminal, the message response and redirection rule update time can be flexibly controlled, thereby avoiding system confusion caused by untimely redirection rule update.

At this point, the message sent by the terminal to the original server will be migrated to the second migration server through redirection, and will no longer be migrated to the first migration server. If a request for migration is required later, the second migration server can be used as the new first migration server to complete the migration by executing the above data processing logic. In this case, the second data request message in the previous migration process corresponds to the first data request message in the next migration process.

It should be noted that, if the second migration server does not agree to the migration, the first migration server can send a migration request to other second migration servers that meet the message response conditions. If there is no second migration server that meets the message response conditions in the server cluster, the first migration server can feedback a prompt message of response failure to the terminal.

The above-mentioned data processing method is that the first migration server that responds to the previous data request message determines the second migration server that responds to the current data request message, and negotiates with the second migration server by sending a migration request. After obtaining the confirmation information fed back by the second migration server, the relocation information is sent to the original server to instruct the original server to redirect the message sent by the terminal to the second migration server. Compared with the traditional technology of centralized migration processing by the original server, it is equivalent to a distributed migration processing method, which can reduce the time loss of multiple migration processes and is conducive to improving data processing efficiency.

In one embodiment, the data processing method further includes: extracting a resource identifier carried in the second data request message; and determining that the first migration server meets the message migration condition when the first migration server does not store the data resource represented by the resource identifier.

Among them, the resource identifier is used to represent the data resource requested by the second data request message. The resource identifier can be, for example, a resource storage address or URI, etc. Specifically, the first migration server can extract the resource identifier carried in the second data request message, and match the resource identifier with the locally stored data resources. If the match is successful, it means that the data resource represented by the resource identifier is stored locally, and the first migration server can meet the data needs of the terminal. At this time, the first migration server does not need to perform subsequent migration processing, but only needs to read the corresponding data resources from the local area and feedback a response message containing the data resources to the terminal. If the match is unsuccessful, it means that the data resource represented by the resource identifier is not stored locally, and the first migration server cannot meet the data needs of the terminal, that is, the first migration server meets the message migration conditions and needs to perform subsequent migration processing.

In this embodiment, whether the first migration server meets the message migration condition is determined based on the resource identifier. The algorithm is simple and can further improve data processing efficiency.

In one embodiment, sending a migration request for a second data request message to a second migration server that meets the message response condition includes: determining a second migration server that meets the message response condition; and sending a migration request for the second data request message to the second migration server.

Specifically, the first migration server may determine a second migration server that meets the message response condition based on the resource identifier extracted from the second data request message, and send a migration request for the second data request message to the second migration server.

In a specific embodiment, the first migration server can determine the message response condition that matches the resource identifier based on the resource amount of the data resource represented by the resource identifier, and can also request content scheduling information corresponding to the resource identifier from the content scheduling center. Then, the first migration server can determine multiple candidate servers that can provide the data resource based on the content scheduling information, and determine the second migration server that meets the message response condition from these candidate servers. The message response condition can refer to the transmission requirement that the available load can meet the resource amount. It can be understood that the larger the resource amount of the data resource represented by the resource identifier, the more available load is required.

In the above embodiment, the message response condition matches the resource identifier, so that the determined second migration server meets the personalized requirements of the second data request message, which can ensure that the data request can be responded to in time, which is conducive to further improving data processing efficiency.

In a specific embodiment, determining the second migration server that meets the message response condition includes: sending a server information acquisition request carrying a resource identifier to a content scheduling center; obtaining a server identifier that the content scheduling center responds to the server information acquisition request and feeds back; and determining the server represented by the server identifier as the second migration server that meets the message response condition.

Among them, please refer to the above for the specific limitations of the content scheduling center, which will not be repeated here. The server identifier is identification information that can uniquely represent the server. The identification information may include information such as IP address, port number, protocol type, etc., which are not limited here. Specifically, the first migration server can send a server information acquisition request carrying a resource identifier to the content scheduling center. The content scheduling center queries the server that can provide transmission services for the data resources requested by the terminal based on the above resource identifier, and then feeds back the server identifier of the server to the first migration server. Then, the first migration server can determine the server represented by the server identifier as the second migration server that meets the message response conditions.

In the above embodiment, the first migration server determines the second migration server that meets the message response condition by interacting with the content scheduling center, which can reduce the load of the first migration server and is conducive to further improving data processing efficiency.

It can be understood that for a certain resource identifier, if the number of server identifiers fed back by the content scheduling center is one, it means that in the current server cluster, only one server can provide the data resource represented by the resource identifier. At this time, the first migration server can determine the server represented by the resource identifier as the second migration server. If the number of server identifiers fed back by the content scheduling center is multiple, it means that in the current server cluster, multiple servers can provide the data resource represented by the resource identifier. At this time, the first migration server needs to perform further screening to determine the second migration server.

In a specific embodiment, the number of server identifiers is multiple. In the case of this embodiment, the server represented by the server identifier is determined as the second migration server that meets the message response condition, including: determining the candidate server represented by each server identifier, and obtaining the load information of each candidate server; determining the candidate server with the smallest load as the second migration server that meets the message response condition.

Specifically, when the first migration server obtains multiple server identifiers from the content scheduling center, it can determine the candidate servers represented by each server identifier and obtain the load information of each candidate server. Then, based on the load information, the candidate server with the smallest load is determined as the second migration server that meets the message response condition.

In this embodiment, when there are multiple candidate servers, the candidate server with the smallest load is determined as the second migration server that meets the message response condition, which can ensure the data processing efficiency of the second migration server.

In one embodiment, as shown in FIG8 , the present application further provides a data processing method, which may be executed by a computer device, and the computer device may be the original server shown in FIG1 , and includes the following steps:

Step S802: receiving a first data request message sent by a terminal, and sending a first redirect message including the first data request message to a first migration server.

The specific limitations of the first data request message and the first redirect message are as mentioned above and will not be repeated here. Specifically, the original server can receive the first data request message sent by the terminal, and when it is unable to provide the data resources requested by the first data request message to the terminal, it can send the first redirect message containing the first data request message to the first migration server.

In a specific embodiment, the redirection message for redirecting the data request message from the terminal to the migration server has the following characteristics: the source address of the message is the IP address of the original server; the destination address of the message is the IP address of the migration server; the source port of the message is the port number of the original server (communicating with the migration server), which is the port number previously negotiated by the two; the destination port of the message is the port number of the migration server (communicating with the original server), which is the port number previously negotiated by the two; the protocol type of the message is the communication protocol type negotiated by the two, including TCP or UDP.

Step S804: receiving a second data request message sent by the terminal.

The second data request message is sent by the terminal when the first response message is received; the first response message is fed back to the terminal by the first migration server based on the first data request message. Specifically, when the terminal receives the first response message fed back by the first migration server based on the first data request message, the terminal can send the second data request message to the original server to request to obtain new data resources. Thus, the original server can receive the second data request message sent by the terminal.

Step S806: Send a second redirection message including a second data request message to the first migration server.

Specifically, the original server can determine the operation for the message according to the five-tuple information of the message. The five-tuple information of the second data request message is the same as the five-tuple information of the first data request message. In the case where the first data request message is redirected to the first migration server, the operation corresponding to the five-tuple information is redirection, so the original server will encapsulate the second data request message into the second redirection message according to the same redirection rule as the first data request message, and send it to the first migration server.

Step S808: When the first migration server meets the message migration condition, receiving redirection information for the second data request message.

The redirection information is sent by the first migration server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server; and the second migration server meets the message response condition. Specifically, when the first migration server meets the message migration condition, the redirection information for the second data request message is received so as to subsequently redirect the message sent by the terminal to the second migration server.

The above-mentioned data processing method is that the first migration server that responds to the previous data request message determines the second migration server that responds to the current data request message, and negotiates with the second migration server by sending a migration request. After obtaining the confirmation information fed back by the second migration server, the relocation information is sent to the original server to instruct the original server to redirect the message sent by the terminal to the second migration server. Compared with the traditional technology of centralized migration processing by the original server, it is equivalent to a distributed migration processing method, which can reduce the time loss of multiple migration processes and is conducive to improving data processing efficiency.

In one embodiment, the data processing method further includes: determining a redirection rule corresponding to the first data request message and a redirection release condition for the redirection rule; and releasing the redirection rule corresponding to the first data request message when the redirection release condition is met.

As described above, the original server can maintain the redirection rule through the five-tuple information. The five-tuple information can represent the connection between the original server and the terminal. The original server can be connected to multiple terminals, corresponding to multiple five-tuple information. In the case where the operation corresponding to the five-tuple information is redirection, the original server stores the redirection rule corresponding to the five-tuple information. The redirection rule is used to indicate the migration object of the message received from the terminal corresponding to the five-tuple information.

Specifically, the original server can determine the redirection rule corresponding to the first data request message and the redirection release condition for the redirection rule according to the five-tuple information of the first data request message. The redirection release condition can be, for example, that the number of changes to the redirection rule reaches a set number of times, or that no associated message is received within a set time. The set time can be configured by an administrator and declared in a configuration file, or a default value, such as 30S, can be used. The original server can determine whether the redirection release condition is currently met based on the interaction situation corresponding to the five-tuple information, and release the redirection rule corresponding to the first data request message when the redirection release condition is met to provide computing resources for other connected terminals.

In the above embodiment, a redirection release condition is configured for the redirection rule, and when the redirection release condition is met, the redirection rule corresponding to the first data request message is released, which can ensure that the computing resources of the original server can be reasonably configured, which is conducive to further improving data processing efficiency.

It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application also provides a data processing system for implementing the data processing method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more data processing system embodiments provided below can refer to the limitations on the data processing method above, and will not be repeated here.

In one embodiment, the data processing system includes an original server, a first migration server, and a second migration server; the original server receives a first data request message sent by a terminal, and sends a first redirect message containing the first data request message to the first migration server; the first migration server feeds back a first response message of the first data request message to the terminal; the original server receives a second data request message sent by the terminal, and sends a second redirect message containing the second data request message to the first migration server; the first migration server sends a migration request for the second data request message to the second migration server that meets the message response condition when the first migration server meets the message migration condition; the first migration server sends redirection information to the original server when receiving confirmation information fed back by the second migration server based on the migration request. The second data request message is sent by the terminal when the first response message is received; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server.

In a specific embodiment, as shown in FIG9 , each server in the server cluster includes a redirector, a migration module and a migration stack, and each server stores data resources. The redirector is used to implement the redirection function. The protocol stack is used to construct a data message that complies with the communication protocol. The migration module is used to perform migration negotiation.

Specifically, before introducing the distributed multiple migrations designed in this application, it is necessary to first explain the traffic delivery process of the previous migration. As shown in Figure 9, the solid line represents the message flow diagram after the existing connection migration is successfully executed (that is, the existing connection has completed at least one connection migration). After the migration, the first migration server passes the data resources to its own protocol stack (such as TCP/IP protocol stack), and the protocol stack constructs a response message with these data resources and delivers the response message to the terminal. The response message carries the data resources requested by the terminal, so it can also be called a traffic message. In the above process, the response message sent by the first migration server to the terminal uses the most original connection information of the connection (that is, the information of the original server and the terminal). After receiving the above response message, the terminal replies with a message confirmation message (ACK message), which is sent to the original server, and the original server redirects the ACK message received from the terminal to the first migration server responsible for the traffic sending service, and the first migration server will perform the subsequent traffic sending and packet loss repair (if any) operations according to the received ACK message.

When the terminal sends a new traffic request, the corresponding data resource does not exist in the first migration server. At this time, the connection needs to be migrated to the server containing the corresponding data resource (referred to as the second migration server) as soon as possible, and the second migration server responds to the terminal's request. Except for the first migration described above, the steps of each migration are as follows: (1.1) The terminal sends a data request message (i.e., the second data request message) based on the existing connection; (1.2) The request message is transmitted to the original server through the network and is "forwarded" to the current migration server (referred to as the first migration server) by the redirector of the original server; (1.3) After receiving the above new request message, the first migration server passes it to the protocol stack through its redirector; (2.1) The protocol stack of the first migration server queries the data resource list and finds that the traffic data requested by the terminal does not exist locally (or the data resource requested by the terminal cannot be obtained locally), and the protocol stack of the first migration server sends a connection migration request to its own migration module; (2.2) At this time, the first migration server obtains the server information that can provide services for the user's latest request through the content scheduling center, which serves as the next target server for connection migration (referred to as the second migration server); (2.3) The migration module sends an update instruction to its own redirector; (3.1) The first migration server sends a connection migration negotiation message to the second migration server; (3.2 ) The negotiation message carries information such as the connection status and application status, which will be used by the protocol stack of the second migration server to respond to user requests; (3.3) After the above connection migration negotiation is completed, the first migration server sends a redirection rule update instruction to the original server, which redirects the message from the terminal to the second migration server; (4) The second migration server sends the corresponding data resources to the terminal based on the user request information carried in the above negotiation process, as well as the transport layer and application layer status; (5.1) After the terminal receives the traffic message it requested, , reply message confirmation message (ACK message), (5.2) the message is "forwarded" by the redirector of the original server to the second migration server; (6.1) the redirector of the second migration server passes the received ACK message to its own protocol stack; (6.2) the protocol stack of the second migration server executes the next traffic message sending or packet loss repair message retransmission (if any); (7) as shown in step (4), the second migration server sends the message that needs to be retransmitted to the terminal; subsequently, steps (5) (6) (7) operations will be executed in sequence until the connection (flow) ends.

The above-mentioned data processing system, when facing multiple data requests and involving multiple requests for migration, determines the second migration server that responds to the current data request message by the first migration server that responds to the previous data request message, and negotiates with the second migration server by sending a migration request. After obtaining the confirmation information fed back by the second migration server, the relocation information is sent to the original server to instruct the original server to redirect the message sent by the terminal to the second migration server. This can realize distributed migration processing, thereby reducing the time loss of multiple migration processes, which is conducive to improving data processing efficiency, and then can more quickly feedback the requested data resources to the terminal, thereby improving the networking capability of the server cluster and the business experience of the terminal.

In one embodiment, the migration request carries connection status information and application status information. In this embodiment, the second migration server is specifically configured to feed back a second response message of the second data request message to the terminal based on the connection status information and the application status information.

The connection status information includes, but is not limited to, the terminal information of the terminal, the server information of the original server, the protocol type, the transport layer status information of the first migration server and the terminal, the message number, etc. The terminal information and the server information may include an IP address, a port number, etc. The transport layer status information of the first migration server may include a sending window value, an amount of data in transit, etc. The transport layer status information of the terminal may include a receiving window value, an effective available bandwidth, etc. The application status information may include a resource identifier of the data resource requested by the second data request message, and may also include a key for encrypting and decrypting user data.

Specifically, the second migration server can determine the configuration information of the second response message based on the connection state information and the application state information, and then feed back the second response message of the second data request message to the terminal based on the configuration information. The configuration information includes but is not limited to five-tuple information, transmission parameters, etc. The transmission parameters may include a sending window and a sending rate, etc.

In this embodiment, the migration request carries the connection status information and the application status information, so that there is no need to send the connection status information and the application status information additionally after the migration negotiation is completed, which can further improve the data processing efficiency.

In one embodiment, the connection state information includes server information of the original server and terminal information of the terminal. In this embodiment, the second migration server is specifically configured to feed back a second response message of the second data request message to the terminal based on the server information and the terminal information.

Specifically, the second migration server can configure the five-tuple information of the message based on the server information and the terminal information, and then feed back the second response message of the second data request message to the terminal. The five-tuple information of the second response message is as follows: the source address is the IP address of the original server; the target address is the IP address of the terminal; the source port number is the port number of the original server; the destination port number is the port number of the terminal; the protocol type is the port number of the original server and the protocol type of the terminal communication. Furthermore, the message number of the second response message can continue the message number of the current connection (the connection between the original server and the terminal), and the message number can be synchronized from the first migration server to the second migration server through the migration request.

In this embodiment, the migration request carries the server information of the original server and the terminal information of the terminal, which can facilitate the second migration server to configure the second response message based on the current connection, so that the terminal will not perceive the migration and continue to obtain data resources by interacting with the original server, which is conducive to improving the convenience of interaction.

In a specific embodiment, the application state information includes a resource identifier and a key. In this embodiment, the second migration server is specifically used to obtain the data resource represented by the resource identifier, encrypt the data resource using the key to obtain an encrypted resource, and feed back a second response message carrying the encrypted resource to the terminal.

The resource identifier is used to represent the data resource requested by the second data request message. Specifically, when the migration request carries a key, it indicates that the requested data needs to be encrypted. Based on this, the second migration server can obtain the data resource represented by the resource identifier, encrypt the data resource using the key to obtain the encrypted resource, and feed back a second response message carrying the encrypted resource to the terminal.

In this embodiment, the application state information includes a resource identifier and a key, which can match the requirements of encryption application scenarios and is conducive to improving the flexibility of the data processing method.

In one embodiment, the connection status information includes transport layer status information of the first migration server and the terminal respectively; the second migration server is specifically configured to determine transmission parameters according to the transport layer status information, and feed back a second response message of the second data request message to the terminal based on the transmission parameters.

The transport layer status information of the first migration server may include the sending window value, the amount of data in transit, etc., and the transport layer status information of the terminal may include the receiving window value, the effective available bandwidth, etc. The transmission parameters may include the sending window and the sending rate, etc. Specifically, in the initial stage of the second migration server sending traffic packets to the terminal, the sending window send_cwnd and the receiving window receive_cwnd synchronized by the first migration server are used to calculate the congestion window cwnd, as shown in formula (1):

cwnd = min{send_cwnd, receive_cwnd} (1)

The second migration server calculates the initial sending window size init_cwnd according to the calculated congestion window cwnd and the in-flight flow inflight_size, as shown in formula (2):

Init_cwnd = cwnd - inflight_size (2)

In the initial stage of sending traffic packets to the terminal, the second migration server uses the effective available bandwidth BtlBW synchronized from the first migration server to configure the initial sending rate init_pacing, as shown in formula (3):

Init_pacing = BtlBW (3)

The above initial sending window size and initial sending rate will no longer be used after the second migration server receives the message confirmation message (ACK message) from the terminal.

In this embodiment, the transmission parameters are determined based on the transport layer status information of each of the first migration server and the terminal, which can ensure the smooth transmission of the second response message, thereby ensuring the reliability of data processing.

In traditional technology, there are many methods for migrating a connection from one server to another, which can be mainly divided into two categories: one is a two-end negotiation migration method; the other is a server single-end migration method.

Bilateral negotiation migration means: after receiving the traffic request message from the terminal, the original server sends the relevant information of the migration server to the terminal; after receiving the above information, the terminal resends the traffic request message to the migration server, and after receiving the above request message, the migration server sends the traffic message as a response to the request; the subsequent terminal and the migration message will interact directly until the connection is closed or the request ends. As shown in Figure 10, after the terminal sends a request message to the original server, it is informed that the original server cannot provide cloud services for the terminal; at the same time, the original server "hopes" that the terminal resends the request message to another server (migration server); at this time, the terminal resends the request message to the above migration server, and the latter sends the requested data resources to the terminal.

This method mainly faces the following problems: the negotiation time between the original server and the terminal is relatively long, and their frequent interactions will seriously affect the time it takes for the terminal to obtain the requested data; for security reasons, the terminal may not support the above-mentioned function of negotiating connection migration with the server, causing the CDN manufacturer to be unable to continue to provide cloud services to the terminal, resulting in service interruption; this is also the main reason why this method cannot be used in a real network environment.

Single-end server migration means that after receiving a request message from a terminal, the original server "actively" contacts another server that can provide services for the terminal and informs it of the connection information and request information. The other server will respond to the terminal's request based on the above information. As shown in Figure 11, after receiving a request message from a terminal, the original server negotiates with another server, which uses the acquired connection information and request information to send a traffic message to the terminal as a response; after receiving the requested traffic message, the terminal sends a message confirmation message to the original server; the original server forwards the message confirmation message to the selected migration server, which will continue to provide cloud services for the terminal.

This method mainly faces the following problems: This method is mainly applicable to the scenario of single connection request, that is, one connection includes only one traffic request; if a complex connection (including multiple requests) is encountered, the migration server will "send back" the request message to the original server after receiving the new request message from the terminal, and the latter will "re-migrate" the connection. During this process, if the original server is unavailable due to upgrade or update, the CDN will not be able to provide cloud service functions for the terminal, resulting in connection interruption and other events that seriously affect the client's business experience.

This application focuses on solving the problem of low migration efficiency and obvious business damage caused by over-reliance on centralized migration server selection when facing multiple requests and multiple data sources. It proposes a distributed lossless migration method that can significantly improve migration efficiency, optimize terminal business experience, and enhance the core competitiveness of CDN manufacturers.

In a specific embodiment, as shown in FIG12 , the implementation process of the present application includes the following steps:

(1) Based on the existing connection, the terminal sends a new traffic request message. The message is redirected to the server after the last connection migration (the first migration server) through the original server. The protocol stack of the server realizes that the connection needs to be migrated to another server.

Among them, the terminal sends a new traffic request message Pkt_req to the original server, and the message carries the identifier URI (Uniform Resource Identifier) of the requested data resource. After receiving the above Pkt_req message, the original server redirects the message to the migration server (referred to as the first migration server) that currently provides the data sending task for the connection. The redirection message Pkt_req_redirect contains the Pkt_req message. Optionally, the redirection operation for the message can be implemented by the server's redirector. This application focuses on how to migrate the connection to other servers that can respond to user requests when the connection has been migrated from the original server to other servers; but when it cannot respond to new traffic requests from the terminal.

Furthermore, the redirection message Pkt_req_redirect that redirects the Pkt_req message from the terminal to the first migration server has the following characteristics: the source address of the Pkt_req_redirect message is the IP address of the original server; the destination address of the Pkt_req_redirect message is the IP address of the first migration server; the source port of the Pkt_req_redirect message is the port number of the original server (communicating with the first migration server); the port number is the port number negotiated by the two before; the destination port of the Pkt_req_redirect message is the port number of the first migration server (communicating with the original server); the port number is the port number negotiated by the two before; the protocol type of the Pkt_req_redirect message is the communication protocol type negotiated by the two, including TCP or UDP.

After receiving the Pkt_req_redirect message from the original server, the first migration server extracts the data resource identifier URI of the traffic request carried in the Pkt_req message in the message, and determines whether the connection needs to be migrated to another server. Optionally, the first migration server will migrate the current connection to another server when the following conditions are met: the server cannot obtain the data resource requested by the terminal locally; the load of the current server (such as CPU utilization, memory usage, traffic size, etc.) is high. If the current migration server needs to migrate the current connection to another server, specifically execute step (2); otherwise, it will obtain the data resource requested by the user and respond to the user's request.

(2) After receiving a new request message from the terminal, if the first migration server determines that it is necessary to perform another migration of the connection, it starts its own migration module. The module first performs the preparation operations before the connection migration, including obtaining the information of the target server (referred to as the second migration server) that meets the message response conditions, resetting the redirection rules for the connection, etc. Specifically, the protocol stack of the first migration server sends an instruction to its migration module to "inform" it that the current connection needs to be migrated; the first migration server obtains the information of the target server from the content scheduling center.

The specific process of the first migration server obtaining the target server information from the content scheduling center may be: the first migration server sends an acquisition request message Pkt_obtain_target to the content scheduling center, and the message carries a URI for identifying the user's request for data resources; the content scheduling center queries the target server information that can provide transmission services for the terminal's request for data resources according to the above URI, that is, the target server has the corresponding data resources, and the load of the target server is not high. The target server information fed back by the content scheduling center includes but is not limited to: the IP address of the target server (IP_target); the port number of the target server (Port_target); the protocol type supported by the target server (Ptl_type_target). The content scheduling center can be a separate server or located inside each server. In particular, the content scheduling center can periodically synchronize its own information for selecting the target server to each server.

Furthermore, the migration module sends a rule for the connection to the redirector of the first migration server, updates the operation for the connection in the redirector to discard, and sets the operation for five_tuple in the redirector to drop. At this time, after receiving the message about the connection from the terminal, the first migration server will perform a discard operation; this operation is used to avoid state confusion before and after the connection migration negotiation process.

(3) The first migration server negotiates the connection migration with the target server, during which the application layer and transport layer status information of the connection are synchronized; and the original server is notified to update the rules of the redirector.

Specifically, the first migration server can send a connection migration request message Pkt_mig_req to the second migration server, wherein the message carries information such as the connection status and the application status. After receiving the Pkt_mig_req message from the first migration server, the migration module of the second migration server passes it to its own protocol stack; the protocol stack of the second migration server initializes the connection to be migrated according to the connection status in Pkt_mig_req. The second migration server queries whether it stores the data resources requested by the terminal according to the URI; and replies to the first migration server with a migration negotiation confirmation message Pkt_mig_ack, wherein the message carries feedback information on whether the second migration server supports the migration of the connection.

If the second migration server supports connection migration, the first migration server sends a response start notification and a redirection rule update instruction to the second migration server and the original server respectively, as follows: after receiving the connection migration confirmation message from the second migration server, the first migration server sends a response start notification to the second migration server, and after receiving the notification information, the latter sends the data resource requested by the terminal based on the initialized connection. After receiving the connection migration confirmation message from the second migration server, the first migration server sends a redirection rule update instruction to the original server, and after receiving the instruction, the latter redirects all subsequent messages of the connection to the second migration server.

(4) After receiving the response start notification from the first migration server, the second migration server uses the connection state and application state synchronized in step (3) to send the data resource requested by the terminal to the terminal.

Specifically, the traffic message (i.e., the second response message) sent by the second migration server to the terminal has the following characteristics: the source address and destination address of the traffic message are the IP address of the original server and the IP address of the terminal respectively; the source port number and destination port number of the traffic message are the port number of the original server and the port number of the terminal respectively; the protocol type of the traffic message is the port number of the original server and the protocol type of the terminal communication; the message number of the traffic message is the message number of the current connection; the above contents are all synchronized from the first migration server to the second migration server during the connection negotiation process. Furthermore, the data carried in the traffic message is the data resource corresponding to the URI carried by the terminal request message Pkt_req; if the data in the traffic message needs to be encrypted, it is encrypted using the key for data encryption and decryption synchronized during the migration negotiation process.

The traffic packets sent from the second migration server to the terminal follow the following sending control rules:

In the initial stage of sending traffic packets to the terminal, the second migration server uses the sending window send_cwnd and receiving window receive_cwnd synchronized from the first migration server to calculate the congestion window cwnd, as shown in formula (1):

cwnd = min{send_cwnd, receive_cwnd} (1)

The second migration server calculates the initial sending window size init_cwnd according to the calculated congestion window cwnd and the in-flight traffic inflight_size, as shown in formula (2):

Init_cwnd = cwnd - inflight_size (2)

In the initial stage of sending traffic packets to the terminal, the second migration server uses the effective available bandwidth BtlBW synchronized from the first migration server to configure the initial sending rate init_pacing, as shown in formula (3):

Init_pacing = BtlBW (3)

The above initial sending window size and initial sending rate will no longer be used after the second migration server receives the message confirmation message (ACK message) from the terminal.

After receiving the traffic message sent from the second migration server, the terminal replies with a message confirmation message Pkt_ack; the message is redirected to the second migration server via the original server. The message redirected from the original server to the second migration server is recorded as Pkt_redirect, which has the following characteristics: the source address and source port are the IP address and port number of the original server respectively; the destination address and destination port are the IP address and port number of the second migration server respectively; the Pkt_redirect message contains all the contents of the Pkt_ack message.

After receiving the Pkt_redirect message redirected by the original server, the second migration server extracts the Pkt_ack message sent by the terminal and determines the next traffic message sending strategy based on the message, as follows: After receiving the Pkt_redirect message, the redirector of the second migration server passes it to the protocol stack; the latter extracts the Pkt_ack message carried by it from the Pkt_redirect message; the protocol stack determines whether packet loss occurs based on the message information received (or not received) by the terminal "declared" in the Pkt_ack message; if packet loss occurs, a packet loss repair operation is performed (the lost message is retransmitted); if packet loss does not occur, the data resources to be sent next are obtained, and data messages continue to be sent to the terminal.

The second migration server continues to send traffic messages (or packet loss repair messages) to the terminal according to the Pkt_ack message. During the sending process, the above traffic messages will no longer follow the initial sending rules or parameters (such as init_cwnd and init_pacing); instead, based on the network quality information (such as packet loss rate, RTT, network bandwidth, etc.) obtained from the Pkt_ack message, the existing congestion control algorithm is used to calculate the latest congestion window cwnd and sending rate pacing to perform the sending of these traffic messages. After receiving the above traffic messages, the terminal can send a confirmation message or initiate a new data request message again until the connection is closed, that is, the terminal is disconnected from the original server.

In this application, when the connection ends, the redirection rule of the original server for the connection will be released (or deleted); in particular, if the server's redirection rule does not encounter a message of the related connection within a time threshold T, it will be automatically released; where the time threshold T can be configured by the administrator and declared in the configuration file. By default, T=30s.

This application enables connections to support flexible and efficient distributed migration methods in the case of multiple requests and multiple data sources. When the server receives a request message from the terminal, it can independently select the target server and migrate the current connection to the target server, without relying on centralized server management and control. This effectively reduces the time loss during multiple connection migrations and improves the efficiency of connection migration, which is conducive to ensuring the client's business experience and enhancing the core competitiveness of CDN manufacturers.

Based on the same inventive concept, the embodiment of the present application also provides a data processing device for implementing the data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more data processing device embodiments provided below can refer to the limitations on the data processing method above, and will not be repeated here.

In one embodiment, as shown in FIG. 13 , a data processing device is provided, which is applied to a first migration server and includes a response message feedback module 1302, a redirect message receiving module 1304, a migration module 1306, and a redirect information sending module 1308, wherein:

A response message feedback module 1302 is used to respond to the first data request message carried in the first redirection message sent by the original server, and feed back a first response message to the terminal that sent the first data request message;

The redirection message receiving module 1304 is used to receive a second redirection message including a second data request message sent by the original server; the second data request message is sent to the original server by the terminal when the first response message is received;

The migration module 1306 is configured to send a migration request for the second data request message to a second migration server that meets the message response condition if the first migration server meets the message migration condition;

The redirection information sending module 1308 is used to send redirection information to the original server when receiving confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server.

In one embodiment, the data processing device further includes a migration judgment module, which is used to: extract a resource identifier carried in the second data request message; and determine that the first migration server meets the message migration condition when the first migration server does not store the data resource. The resource identifier is used to represent the data resource requested by the second data request message.

In one embodiment, the migration module 1306 includes: a server determination submodule, used to determine a second migration server that meets the message response condition; the message response condition matches the resource identifier; and a migration request sending submodule, used to send a migration request for the second data request message to the second migration server.

In one embodiment, the server determination submodule is specifically used to: send a server information acquisition request carrying a resource identifier to the content scheduling center; obtain the server identifier fed back by the content scheduling center in response to the server information acquisition request; and determine the server represented by the server identifier as the second migration server that meets the message response condition.

In one embodiment, there are multiple server identifiers. In this embodiment, the server determination submodule is specifically used to: determine the candidate server represented by each server identifier, and obtain the load information of each candidate server; determine the candidate server with the smallest load as the second migration server that meets the message response conditions.

In one embodiment, the data processing device further includes a response start notification module, which is used to send a response start notification to the second migration server upon receiving confirmation information fed back by the second migration server based on the migration request; the response start notification is used to instruct the second migration server to feed back a second response message to the second data request message to the terminal.

In one embodiment, the data processing device also includes a packet loss repair module, which is used to: obtain a confirmation message fed back by the terminal based on the first response message; the confirmation message is received by the original server from the terminal and redirected to the first migration server; when it is determined based on the confirmation message that the first response message has packet loss, perform a packet loss repair operation on the first response message.

In one embodiment, as shown in FIG. 14 , the present application further provides another data processing device, which is applied to an original server. The device includes a data request message receiving module 1402, a redirect message sending module 1404, and a redirect information receiving module 1406, wherein:

The data request message receiving module 1402 is used to receive a first data request message sent by a terminal;

A redirection message sending module 1404, configured to send a first redirection message including a first data request message to a first migration server;

The data request message receiving module 1402 is further configured to receive a second data request message sent by the terminal; the second data request message is sent by the terminal after receiving the first response message; the first response message is fed back to the terminal by the first migration server based on the first data request message;

The redirection message sending module 1404 is further configured to send a second redirection message including a second data request message to the first migration server;

The redirection information receiving module 1406 is used to receive redirection information for the second data request message when the first migration server meets the message migration condition; the redirection information is sent by the first migration server when receiving the confirmation information fed back by the second migration server based on the migration request; the redirection information is used to instruct the original server to redirect the message sent by the terminal to the second migration server; the second migration server meets the message response condition.

In one embodiment, the data processing device also includes a redirection release module, which is used to: determine the redirection rule corresponding to the first data request message, and the redirection release condition for the redirection rule; when the redirection release condition is met, release the redirection rule corresponding to the first data request message.

Each module in the above data processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG15. The computer device includes a processor, a memory, an input/output interface (Input/Output, referred to as I/O) and a communication interface. The processor, the memory and the input/output interface are connected via a system bus, and the communication interface is connected to the system bus via the input/output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data involved in the above-mentioned data processing method. The input/output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data processing method is implemented.

Those skilled in the art will understand that the structure shown in FIG. 15 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards in the relevant regions and areas. In addition, the subject can choose not to authorize the subject information and related data, or refuse or conveniently refuse to push information, etc.

In this application, when collecting and processing relevant data during the instance application, the requirements of relevant local laws and regulations should be strictly followed to obtain the informed consent or separate consent of the personal information subject, and subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims (19)

1. A data processing method, applied to a first migration server, the method comprising:

Responding to a first data request message carried in a first redirection message sent by an original server, and feeding back a first response message to a terminal sending the first data request message;

Receiving a second redirection message which is sent by the original server and contains a second data request message; the second data request message is sent to the original server by the terminal under the condition that the first response message is received;

If the first migration server meets the message migration conditions, a migration request aiming at the second data request message is sent to a second migration server meeting the message response conditions;

Sending redirection information to the original server under the condition that confirmation information fed back by the second migration server based on the migration request is received; the redirection information is used for indicating the original server to redirect the message sent by the terminal to the second migration server.

2. The method according to claim 1, wherein the method further comprises:

Extracting a resource identifier carried in the second data request message; the resource identifier is used for representing the data resource requested by the second data request message;

and under the condition that the first migration server does not store the data resource, determining that the first migration server meets the message migration condition.

3. The method according to claim 2, wherein the sending a migration request for the second data request message to a second migration server that satisfies a message response condition includes:

Determining a second migration server meeting the message response condition; the message response condition is matched with the resource identifier;

And sending a migration request for the second data request message to the second migration server.

4. The method of claim 3, wherein the determining a second migration server that satisfies the message response condition comprises:

Sending a server information acquisition request carrying the resource identifier to a content scheduling center;

Acquiring a server identifier of the content scheduling center in response to the server information acquisition request and feedback;

and determining the server identification represented by the server as a second migration server meeting the message response condition.

5. The method of claim 4, wherein the number of server identifications is a plurality; the determining the server identified by the server identifier as a second migration server meeting the message response condition comprises the following steps:

determining each server to identify each characterized candidate server, and acquiring each load information of each candidate server;

and determining the candidate server with the smallest load as a second migration server meeting the message response condition.

6. The method according to any one of claims 1 to 5, further comprising:

Sending a response start notification to the second migration server under the condition that confirmation information fed back by the second migration server based on the migration request is received;

And the response starting notice is used for indicating the second migration server to feed back a second response message of the second data request message to the terminal.

7. The method according to any one of claims 1 to 5, further comprising:

Acquiring a confirmation message fed back by the terminal based on the first response message; the confirmation message is received from the terminal by the original server and redirected to the first migration server;

and executing packet loss repairing operation for the first response message under the condition that the packet loss of the first response message is determined based on the confirmation message.

8. A data processing method, applied to an origin server, the method comprising:

receiving a first data request message sent by a terminal, and sending a first redirection message containing the first data request message to a first migration server;

receiving a second data request message sent by the terminal; the second data request message is sent by the terminal under the condition of receiving the first response message; the first response message is fed back to the terminal by the first migration server based on the first data request message;

Sending a second redirection message containing the second data request message to the first migration server;

Receiving redirection information aiming at the second data request message under the condition that the first migration server meets the message migration condition; the redirection information is sent by the first migration server under the condition that confirmation information fed back by the second migration server based on the migration request is received; the redirection information is used for indicating the original server to redirect the message sent by the terminal to the second migration server; and the second migration server meets the message response condition.

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

determining a redirection rule corresponding to the first data request message and a redirection release condition aiming at the redirection rule;

And under the condition that the redirection release condition is met, releasing the redirection rule corresponding to the first data request message.

10. A data processing system, the system comprising an origin server, a first migration server, and a second migration server;

the original server receives a first data request message sent by a terminal and sends a first redirection message containing the first data request message to the first migration server;

The first migration server feeds back a first response message of the first data request message to the terminal;

The original server receives a second data request message sent by the terminal and sends a second redirection message containing the second data request message to the first migration server; the second data request message is sent by the terminal under the condition of receiving the first response message;

the first migration server sends a migration request aiming at the second data request message to a second migration server meeting the message response condition under the condition that the first migration server meets the message migration condition;

The first migration server sends redirection information to the original server under the condition that confirmation information fed back by the second migration server based on the migration request is received; the redirection information is used for indicating the original server to redirect the message sent by the terminal to the second migration server.

11. The system of claim 10, wherein the migration request carries connection status information and application status information;

the second migration server is configured to feed back a second response message of the second data request message to the terminal based on the connection status information and the application status information.

12. The system according to claim 11, wherein the connection state information includes server information of the origin server, and terminal information of the terminal;

The second migration server is specifically configured to configure and feed back a second response message of the second data request message to the terminal based on the server information and the terminal information.

13. The system of claim 11, wherein the application state information includes a resource identification and a key; the resource identifier is used for representing the data resource requested by the second data request message;

The second migration server is specifically configured to obtain the data resource represented by the resource identifier, encrypt the data resource with the key to obtain an encrypted resource, and feed back a second response message carrying the encrypted resource to the terminal.

14. The system of claim 11, wherein the connection state information comprises transport layer state information of each of the first migration server and the terminal;

The second migration server is specifically configured to determine a transmission parameter according to each transmission layer status information, and feed back a second response message of the second data request message to the terminal based on the transmission parameter.

15. A data processing apparatus for application to a first migration server, the apparatus comprising:

The response message feedback module is used for responding to a first data request message carried in a first redirection message sent by the original server and feeding back a first response message to a terminal sending the first data request message;

The redirection message receiving module is used for receiving a second redirection message which is sent by the original server and contains a second data request message; the second data request message is sent to the original server by the terminal under the condition that the first response message is received;

The migration module is used for sending a migration request aiming at the second data request message to a second migration server meeting the message response condition if the first migration server meets the message migration condition;

The redirection information sending module is used for sending redirection information to the original server under the condition that confirmation information fed back by the second migration server based on the migration request is received; the redirection information is used for indicating the original server to redirect the message sent by the terminal to the second migration server.

16. A data processing apparatus for application to an origin server, the apparatus comprising:

The data request message receiving module is used for receiving a first data request message sent by the terminal;

The redirection message sending module is used for sending a first redirection message containing the first data request message to a first migration server;

The data request message receiving module is further used for receiving a second data request message sent by the terminal; the second data request message is sent by the terminal under the condition of receiving the first response message; the first response message is fed back to the terminal by the first migration server based on the first data request message;

The redirection message sending module is further configured to send a second redirection message including the second data request message to the first migration server;

The redirection information receiving module is used for receiving redirection information aiming at the second data request message under the condition that the first migration server meets the message migration condition; the redirection information is sent by the first migration server under the condition that confirmation information fed back by the second migration server based on the migration request is received; the redirection information is used for indicating the original server to redirect the message sent by the terminal to the second migration server; and the second migration server meets the message response condition.

17. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 9 when the computer program is executed.

18. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 9.

19. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 9.