CN117354312A

CN117354312A - Access request processing method, device, system, computer equipment and storage medium

Info

Publication number: CN117354312A
Application number: CN202311281618.5A
Authority: CN
Inventors: 吴滢; 仝建刚; 李嫚; 黄君雅; 李智鹏
Original assignee: China Telecom Technology Innovation Center; China Telecom Corp Ltd
Current assignee: China Telecom Technology Innovation Center; China Telecom Corp Ltd
Priority date: 2023-09-28
Filing date: 2023-09-28
Publication date: 2024-01-05

Abstract

The present application relates to an access request processing method, apparatus, system, computer device, storage medium and computer program product. The method comprises the following steps: receiving a plurality of first access requests aiming at a target domain name, which are sent by a core network switch; based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server, and respectively obtaining target load balancing parameters corresponding to each server; determining target service ends corresponding to the first access requests respectively from the service ends based on target load balancing parameters corresponding to the service ends respectively; and sending the access addresses of the target service ends corresponding to the first access requests to the core network switch respectively, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses. By adopting the method, the processing efficiency of the access request can be improved.

Description

Access request processing method, device, system, computer equipment and storage medium

Technical Field

The present invention relates to the field of computer technology, and in particular, to a method, an apparatus, a system, a computer device, a storage medium, and a computer program product for processing an access request.

Background

With the development of enterprises, the scale of a business system and a service platform is larger and larger, when a large number of client requests are received by a large-scale system, a network congestion state is easy to appear, and if a server for responding to the client requests in the system is in the network congestion state for a long time, the response speed of an access request is reduced.

According to the traditional method, each client request is allocated to a corresponding server through core network equipment according to a pre-configured routing strategy, and when the server is blocked, operation and maintenance personnel manually dispatch and forward the client request, so that the problem of low processing efficiency of the access request exists.

Disclosure of Invention

In view of the foregoing, it is desirable to provide an access request processing method, apparatus, system, computer device, computer readable storage medium, and computer program product that can improve the efficiency of access request processing.

The application provides an access request processing method. The method comprises the following steps:

receiving a plurality of first access requests aiming at a target domain name, which are sent by a core network switch; the plurality of first access requests are sent by the plurality of clients to the core network switch;

Determining respective expected resource occupancy rates of the servers corresponding to the target domain name based on the resource occupancy information corresponding to the first access requests;

based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server, and respectively obtaining target load balancing parameters corresponding to each server;

determining target service ends corresponding to the first access requests respectively from the service ends based on target load balancing parameters corresponding to the service ends respectively;

and sending the access addresses of the target service ends corresponding to the first access requests to the core network switch respectively, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses.

The application also provides an access request processing device. The device comprises:

the access request receiving module is used for receiving a plurality of first access requests aiming at the target domain name and sent by the core network switch; the plurality of first access requests are sent by the plurality of clients to the core network switch;

the expected occupancy rate determining module is used for determining the respective expected resource occupancy rate of each server corresponding to the target domain name based on the resource occupancy information corresponding to each first access request;

The load balancing parameter determining module is used for adjusting initial load balancing parameters corresponding to the server side based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server side, and respectively obtaining target load balancing parameters corresponding to each server side;

the target server determining module is used for determining target servers corresponding to the first access requests respectively from the servers based on target load balancing parameters corresponding to the servers respectively;

the access address sending module is used for sending the access addresses of the target service ends corresponding to the first access requests to the core network switch respectively, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses.

The application also provides an access request processing system, which comprises a core network switch, domain name resolution equipment, a plurality of clients and a plurality of servers:

the client is used for sending a first access request aiming at the target domain name to the core network switch;

the core network switch is used for receiving first access requests respectively sent by a plurality of clients and sending the first access requests to the domain name resolution equipment;

The domain name resolution device is used for determining respective expected resource occupancy rates of the service terminals corresponding to the target domain names based on the resource occupancy information corresponding to the first access requests, adjusting initial load balancing parameters corresponding to the service terminals based on occupancy rate differences between the current resource occupancy rates and the expected resource occupancy rates corresponding to the same service terminal, respectively obtaining target load balancing parameters corresponding to the service terminals, respectively determining target service terminals corresponding to the first access requests from the service terminals based on the target load balancing parameters corresponding to the service terminals, and sending access addresses of the target service terminals corresponding to the first access requests to the core network switch;

the core network switch is further configured to send each first access request to a corresponding target server respectively based on the access address of the target server corresponding to each first access request respectively;

and the server is used for responding to the first access request sent by the core network switch.

A computer device comprising a memory storing a computer program and a processor implementing the steps of the above described access request processing method when the processor executes the computer program.

A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described access request processing method.

A computer program product comprising a computer program which, when executed by a processor, implements the steps of the above access request processing method.

According to the access request processing method, the device, the system, the computer equipment, the storage medium and the computer program product, the plurality of first access requests for the target domain name sent by the core network switch are received, and the respective expected resource occupancy rate of each server corresponding to the target domain name is determined based on the resource occupancy information respectively corresponding to each first access request. And according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server, and respectively obtaining the load balancing parameters corresponding to each server. And determining the target service ends corresponding to the first access requests respectively from the service ends based on the target load balancing parameters corresponding to the service ends respectively. And sending the access addresses of the target service ends corresponding to the first access requests to the core network switch respectively, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses. In this way, based on the resource occupancy rates respectively corresponding to the first access requests for the target domain names, the expected resource occupancy rates respectively corresponding to the service ends corresponding to the target domain names are estimated, the initial load balancing parameters corresponding to the service ends are adjusted according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service ends to obtain target load balancing parameters, the first access requests corresponding to the target domain names are distributed based on the target load balancing parameters, the purpose of timely adjusting the load balancing parameters according to the current actual load conditions of the service ends is achieved, the access requests are distributed according to the load balancing parameters updated in real time, the resource loads of the service ends can be more balanced, and the processing efficiency of the access requests is improved.

Drawings

FIG. 1 is an application environment diagram of a method of processing an access request in one embodiment;

FIG. 2 is a flow diagram of a method of processing an access request in one embodiment;

FIG. 3 is a flow diagram of the access request scheduling steps in one embodiment;

FIG. 4 is a schematic diagram of an access request processing system in one embodiment;

FIG. 5 is a schematic diagram of an access request processing system in another embodiment;

FIG. 6 is a schematic diagram of server-side failure response in one embodiment

FIG. 7 is a schematic diagram of a domain name resolution device non-responsive disaster recovery in one embodiment;

FIG. 8 is a block diagram of an access request processing apparatus in one embodiment;

FIG. 9 is a block diagram showing an access request processing apparatus according to another embodiment;

fig. 10 is an internal structural view of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The access request processing method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. The client 102, the core network switch 104, the domain name resolution device 106, and the server 108 communicate with each other through a network. The client 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, which may be smart televisions, smart car devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The domain name resolution device 106 and the server 108 may be implemented as separate servers or as a server cluster composed of a plurality of servers. The client 102, the core network switch 104, the domain name resolution device 106, and the server 108 may be directly or indirectly connected through wired or wireless communication, which is not limited herein.

The client, the core network switch, the domain name resolution device and the server are cooperatively used for executing the access request processing method provided by the embodiment of the application. The method comprises the steps that a plurality of clients respectively send first access requests aiming at target domain names to a core network switch, and the core network switch sends the received first access requests aiming at the target domain names and respectively sent by the clients to domain name resolution equipment. The domain name resolution device receives a plurality of first access requests for the target domain name sent by the core network switch, and determines the respective expected resource occupancy rate of each server corresponding to the target domain name based on the resource occupancy information respectively corresponding to each first access request. The domain name resolution device receives the current resource occupancy rate sent by each server, adjusts initial load balancing parameters corresponding to the server based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, and obtains target load balancing parameters corresponding to each server. The domain name resolution device determines target service ends corresponding to the first access requests respectively from the service ends corresponding to the target domain names based on the target load balancing parameters corresponding to the service ends respectively, and sends the access addresses of the target service ends corresponding to the first access requests respectively to the core network switch. The core network switch sends each first access request to a corresponding target server based on the access address of the target server corresponding to the first access request returned by the domain name resolution device.

In one embodiment, as shown in fig. 2, there is provided an access request processing method, which is described by taking application of the method to a domain name resolution device as an example, the access request processing method includes the following steps:

step S202, receiving a plurality of first access requests for a target domain name sent by a core network switch; the plurality of first access requests are sent by the plurality of clients to the core network switch.

The core network switch is a hardware device for analyzing a destination address in a data packet and forwarding the data packet to the destination address, specifically, when an access request for a target domain name is received, firstly, an access address corresponding to the target domain name is obtained from a domain name resolution device, and then the access request is sent to a server corresponding to the access address, so that data exchange between devices with different IP addresses (Internet Protocol Address, internet protocol addresses) is realized. The domain name refers to the name of a certain computer or a computer cluster on the internet, which is composed of a series of names separated by dots, and is used for positioning identification for positioning the computer during data transmission. The target domain name refers to a domain name for which an access request needs to be processed. The first access request refers to a request for accessing a designated website, which is sent by the client under the normal working state of the domain name resolution device. The domain name resolution device stores domain names and corresponding IP addresses of all servers in the network and has a server for converting the domain names into IP addresses, and the domain name resolution device can be realized by an independent server or a server cluster formed by a plurality of servers.

The core network switch receives first access requests respectively sent by a plurality of clients, and sends the first access requests to the domain name resolution device. The domain name resolution device receives a plurality of first access requests sent by the core network switch and carries out corresponding processing on each first access request aiming at the same domain name. Firstly, a plurality of first access requests for target domain names sent by a core network switch are obtained, in each service end corresponding to the target domain names, a corresponding target service end is determined for each first access request for the target domain names, and then the access address of the target service end corresponding to the first access request is sent to the core network switch, so that the core network switch sends the first access request to the corresponding target service end based on the access address corresponding to the first access request.

Step S204, based on the resource occupation information corresponding to each first access request, determining the respective expected resource occupation rate of each server corresponding to the target domain name.

The resource occupation information refers to computer resources expected to be consumed by the server for processing the first access request, and specifically may be occupation situations of resources such as a CPU, a GPU, and a memory of the server by the first access request. The resource occupancy rate refers to a resource load condition of the server, and specifically may be a CPU load, a memory load, or a resource occupancy rate obtained by integrating at least one of the CPU load, the GPU load, and the memory load. The expected resource occupancy rate refers to that each first access request aiming at the target domain name is uniformly distributed to each service end corresponding to the target domain name, and each service end corresponds to the expected resource occupancy rate respectively and is used for representing the resource occupancy rate respectively corresponding to each service end corresponding to the target domain name under ideal conditions. For example, each first access request for the target domain name is evenly distributed to three servers corresponding to the target domain name, and based on the resource occupation information corresponding to each first access request distributed to each server, it may be determined that the expected resource occupation rates respectively corresponding to the three servers are all 10%.

The domain name resolution device obtains resource occupation information corresponding to each first access request for the target domain name. And calculating the expected resource occupancy rate corresponding to each server when each first access request aiming at the target domain name is evenly distributed to each server corresponding to the target domain name.

Step S206, based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, the initial load balancing parameters corresponding to the server are adjusted, and the target load balancing parameters corresponding to the servers are obtained respectively.

The current resource occupancy rate refers to the actual resource occupancy rate currently corresponding to the server side. The occupancy rate difference refers to a difference between a current resource occupancy rate and an expected resource occupancy rate corresponding to the server, and specifically, when the resource occupancy rate is a CPU occupancy rate, the occupancy rate difference is a difference between the current resource occupancy rate and the expected resource occupancy rate. The load balancing parameter is a parameter which is configured for each server corresponding to the same domain name and used for indicating how to distribute the access request in each server corresponding to the same domain name. The initial load balancing parameter refers to an initial load balancing parameter corresponding to the server. The target load balancing parameter is a load balancing parameter obtained after the initial load balancing parameter is adjusted.

The domain name resolution device obtains the current resource occupancy rate corresponding to each server corresponding to the target domain name. And comparing the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server to obtain the occupancy rate difference corresponding to each server. And based on the occupancy rate difference corresponding to the server, adjusting initial load balancing parameters corresponding to the server to obtain target load balancing parameters corresponding to each server respectively. Specifically, at least one of an initial request dispatch proportion and an initial request dispatch interval in initial load balance parameters corresponding to the server may be adjusted based on the occupancy rate difference corresponding to the server, so as to obtain target load balance parameters corresponding to the server. For example, when the current resource occupancy rate corresponding to the server is greater than the expected resource occupancy rate and the occupancy rate difference is greater than a certain threshold, the initial request dispatch proportion in the initial load balance parameters corresponding to the server is reduced based on the occupancy rate difference, so as to obtain the target load balance parameters corresponding to the server.

In one embodiment, the domain name resolution device monitors the occupancy rate difference corresponding to each server corresponding to the target domain name in real time, and adjusts the initial load balancing parameters corresponding to each server according to the occupancy rate difference corresponding to each server corresponding to the target domain name when the current resource occupancy rate is greater than the expected resource occupancy rate and the occupancy rate difference is greater than a preset value, so as to obtain the corresponding target load balancing parameters. Therefore, the load balancing parameters of the server can be prevented from being updated each time the resource occupancy rate of the server fluctuates, and computer resources can be effectively saved. And further, determining the target service ends corresponding to the first access requests respectively based on the target load balancing parameters corresponding to the service ends respectively. If the occupancy rate difference corresponding to the server side is smaller than or equal to a preset value, the initial load balancing parameters corresponding to the server side do not need to be updated.

Step S208, determining the target service ends corresponding to the first access requests respectively from the service ends based on the target load balancing parameters corresponding to the service ends respectively.

The target server corresponding to the first access request refers to a server which is determined in each server corresponding to the target domain name and is used for processing the first access request.

The domain name resolution device distributes each first access request for the target domain name to each server corresponding to the target domain name according to the target load balancing parameters corresponding to each server respectively corresponding to the target domain name, so as to obtain the target server corresponding to each first access request respectively.

Step S210, the access addresses of the target service ends corresponding to the first access requests are sent to the core network switch, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses.

The access address refers to an IP address of the server.

The domain name resolution device determines a target server corresponding to the first access request, and sequentially sends access addresses of the target servers corresponding to the first access requests for the target domain name to the core network switch, so that the core network switch sends the first access request to the corresponding target server according to the access address corresponding to the received first access request.

In the above access request processing method, by receiving a plurality of first access requests for the target domain name sent by the core network switch, the respective expected resource occupancy rate of each server corresponding to the target domain name is determined based on the resource occupancy information respectively corresponding to each first access request. And according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server, and respectively obtaining the load balancing parameters corresponding to each server. And determining the target service ends corresponding to the first access requests respectively from the service ends based on the target load balancing parameters corresponding to the service ends respectively. And sending the access addresses of the target service ends corresponding to the first access requests to the core network switch respectively, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses. In this way, based on the resource occupancy rates respectively corresponding to the first access requests for the target domain names, the expected resource occupancy rates respectively corresponding to the service ends corresponding to the target domain names are estimated, the initial load balancing parameters corresponding to the service ends are adjusted according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service ends to obtain target load balancing parameters, the first access requests corresponding to the target domain names are distributed based on the target load balancing parameters, the purpose of timely adjusting the load balancing parameters according to the current actual load conditions of the service ends is achieved, the access requests are distributed according to the load balancing parameters updated in real time, the resource loads of the service ends can be more balanced, and the processing efficiency of the access requests is improved.

In one embodiment, based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server, to obtain target load balancing parameters corresponding to each server, respectively, including:

aiming at any one of the service terminals, based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service terminal, the initial request dispatch proportion and the initial request dispatch interval contained in the initial load balancing parameter corresponding to the service terminal are adjusted to obtain the target request dispatch proportion and the target request dispatch interval corresponding to the service terminal, and the target load balancing parameter corresponding to the service terminal is formed;

wherein, the target request dispatch proportion and the occupancy rate difference are in negative correlation, and the target request dispatch interval and the occupancy rate difference are in positive correlation; the target request dispatch proportion is used for indicating the proportion of the first access requests dispatched to the server in each first access request, and the target request dispatch interval is used for indicating the duration of the interval required for dispatching the first access requests to the server.

The request dispatch proportion refers to a request dispatch proportion set for each server corresponding to the same domain name, and is used for indicating how many first access requests should be dispatched for each server corresponding to the domain name. For example, when the target domain name corresponds to three servers, the request dispatch proportions to which the three servers respectively correspond may be set to 33%, and 34%. The request dispatching interval refers to a time interval for dispatching the first access request to the same server, for example, the request dispatching interval corresponding to the server may be set to 5ms, and the next first access request is dispatched to the server every 5 ms. The initial request dispatch proportion refers to an initial request dispatch proportion corresponding to the server. The initial request dispatch interval refers to an initial request dispatch interval corresponding to the server. The target request dispatch ratio refers to a request dispatch ratio obtained after the initial request dispatch ratio corresponding to the server side is adjusted. The target request dispatching interval refers to a request dispatching interval obtained after the initial request dispatching interval corresponding to the server side is adjusted.

For example, the domain name resolution device adjusts an initial request dispatch proportion and an initial request dispatch interval corresponding to the server based on an occupancy rate difference between a current resource occupancy rate and an expected resource occupancy rate corresponding to the server, for any one of the servers corresponding to the target domain name, so as to obtain a target request dispatch proportion and a target request dispatch interval corresponding to the server, where the target request dispatch proportion and the target request dispatch interval form a target load balancing parameter corresponding to the server. Specifically, based on the occupancy rate difference and the preset dispatch proportion weight corresponding to the server, the initial request dispatch proportion in the initial load balancing parameters corresponding to the server is adjusted, based on the occupancy rate difference and the preset dispatch interval weight, the initial request dispatch interval in the initial load balancing parameters corresponding to the server is adjusted, the target load balancing parameters corresponding to the server are obtained, the occupancy rate difference and the target request dispatch proportion are in negative correlation, and the occupancy rate difference and the target request dispatch interval are in positive correlation. When the current resource occupancy rate corresponding to the server side is smaller than the expected resource occupancy rate, the request distribution ratio corresponding to the server side can be increased, and when the current resource occupancy rate corresponding to the server side is smaller than the expected resource occupancy rate, the request distribution ratio corresponding to the server side is increased, and the request distribution interval corresponding to the server side is reduced.

For example, when the target domain name corresponds to three servers, namely, server a, server B, and server C, the initial request dispatch proportions corresponding to server a, server B, and server C are determined to be 33%, and 34%, respectively, according to the equal proportion configuration, and the initial request dispatch intervals are all 1ms. When a plurality of first access requests aiming at the target domain name are acquired, the expected resource occupancy rates respectively corresponding to the server A, the server B and the server C are determined to be 30%. In the running process, if the current resource occupancy rates corresponding to the server A, the server B and the server C are detected to be 10%, 40% and 60%, respectively, the initial request dispatch proportion and the initial request dispatch interval corresponding to the server are adjusted according to the current resource occupancy rate and the expected resource occupancy rate corresponding to the server. And determining that the target request dispatch proportions respectively corresponding to the server A, the server B and the server C are respectively 50%, 30% and 20%, and the initial request dispatch intervals are respectively 1ms, 5ms and 10ms.

In the above embodiment, according to the difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the server, the initial request dispatch proportion and the initial request dispatch interval in the initial load balancing parameters corresponding to the server are adjusted in time, so that the resource loads corresponding to the server can be effectively adjusted in time from the angles of adjusting the number of access requests allocated to the server and the frequency of allocating the access requests, so that the resource loads corresponding to the server are more balanced, and the processing efficiency of the access requests is improved.

In one embodiment, as shown in fig. 3, the access request processing method further includes:

step S302, when detecting that a fault server exists in each server corresponding to the target domain name, determining an update server corresponding to an access request to be scheduled and corresponding to the fault server from the rest normal servers based on the current resource occupancy rate corresponding to the server.

Step S304, the access address of the update server corresponding to the access request to be scheduled is sent to the core network switch, so that the core network switch sends the access request to be scheduled to the update server based on the access address corresponding to the update server.

Step S306, a call task for the fault server is established until the fault server returns to normal; the calling task is used for acquiring the working state of the fault server.

The failure server indicates a server that fails, and specifically, when the communication connection between the server and the domain name resolution device is interrupted, the server may be determined as the failure server when the first access request sent to the server is not responded over time, or when the server refuses to connect. The access request to be scheduled corresponding to the fault server side refers to a first access request which is not responded by the fault server side after being sent to the fault server side. The update server refers to a server which is redetermined for the access request to be scheduled and is used for processing the access request to be scheduled. The call task is a task established when the server fails and used for acquiring the working state of the failed server, and the call task is ended until the failed server returns to the normal state.

The domain name resolution device schedules the access request to be scheduled corresponding to the fault server when detecting that the fault server exists in each server corresponding to the target domain name. Specifically, the current resource occupancy rates corresponding to the normal service ends corresponding to the target domain name are obtained, and the normal service end with the minimum current resource occupancy rate is determined to be the update service end corresponding to the access request to be scheduled. And then the access address of the update server corresponding to the access request to be scheduled is sent to the core network switch, so that the core network switch sends the access request to be scheduled to the corresponding update server based on the access address of the update server. And further establishing a call task between the fault server and the fault server, continuously interacting with the fault server based on the call task timing until the fault server is determined to restore to a normal working state, and ending the call task. Before the fault server returns to the normal state, the corresponding update server needs to be redetermined for each access request distributed to the fault server until the fault server returns to the normal state, and the access request sent to the fault server does not need to be scheduled.

In the above embodiment, when the presence of the failed server in each server corresponding to the target domain name is detected, the to-be-scheduled access request corresponding to the failed server is allocated to the normal server with the lowest current resource occupancy rate based on the current resource occupancy rates respectively corresponding to the normal servers corresponding to the target domain name, so that the to-be-scheduled access request can be responded in time, and the access request processing efficiency is improved.

In one embodiment, the core network switch is further configured to send, when receiving an emergency communication request sent by a server corresponding to the target domain name, a second access request sent by the client and carrying domain name resolution information corresponding to the target domain name to the server indicated by the domain name resolution information; the emergency communication request is sent when the domain name resolution device fails, the second access request is sent when the domain name resolution device fails, and the domain name resolution information is cached locally by the client based on the access path of the first access request that was successfully accessed.

The emergency communication request is an emergency communication request sent to the core network switch by the server when the domain name resolution equipment fault is monitored, and is used for informing the core network switch of the domain name resolution equipment fault and indicating the core network switch to start temporary routing based on domain name resolution information. The second access request is an access request which is sent to the core network switch by the client when the domain name resolution device fails and carries domain name resolution information corresponding to the target domain name. The access path refers to a route path corresponding to a first access request which is cached in a local route log set by the client and is successfully accessed. The domain name resolution information refers to a mapping relationship between the target domain name obtained by resolution and the access address of the server from the routing path of the last first access request of the client to the target domain name, which is cached locally by the client.

The server side sends an emergency communication request to the core network switch when detecting the fault of the domain name resolution equipment. When the core network switch receives an emergency communication request sent by a server, a temporary route based on domain name resolution information is started. When receiving a second access request sent by the client, the core network switch determines an access address of a server corresponding to the target domain name based on domain name resolution information corresponding to the target domain name carried in the second access request, and sends the second access request to the access address corresponding to the target domain name in the domain name resolution information. Meanwhile, the service end monitors the working state of the domain name resolution equipment in real time, and when the domain name resolution equipment is monitored to be recovered to be normal, the core network switch is informed to close the temporary route based on the domain name resolution information.

In the above embodiment, when the domain name resolution device fails, when the client sends an access request for a target domain name, the client first obtains, from the locally cached route log set, a route path corresponding to the first access request for the target domain name, where the last access was successful, resolves domain name resolution information corresponding to the target domain name from the route path, and sends a second access request carrying domain name resolution information corresponding to the target domain name to the core network switch. Meanwhile, when the domain name resolution equipment fails, the core network switch starts temporary routing, and sends a second access request to a server indicated by domain name resolution information according to the domain name resolution information carried in the second access request. When the domain name resolution equipment fails and the core network switch cannot resolve the access address corresponding to the target domain name through the domain name resolution equipment, temporary routing is performed according to the domain name resolution information carried in the second access request, and reliability and stability of access request processing are improved.

In one embodiment, as shown in fig. 4, an access request processing system is provided, the access request processing system comprising a core network switch 402, a domain name resolution device 404, a plurality of clients 406, and a plurality of servers 408:

a client 406, configured to send a first access request for a target domain name to a core network switch;

a core network switch 402, configured to receive first access requests sent by a plurality of clients, and send each first access request to a domain name resolution device;

the domain name resolution device 404 is configured to determine respective expected resource occupancy rates of respective service ends corresponding to the target domain name based on the resource occupancy information respectively corresponding to the respective first access requests, adjust initial load balancing parameters corresponding to the service ends based on occupancy rate differences between the current resource occupancy rates and the expected resource occupancy rates corresponding to the same service end, respectively obtain target load balancing parameters corresponding to the respective service ends, determine target service ends respectively corresponding to the respective first access requests from the respective service ends based on the target load balancing parameters respectively corresponding to the respective service ends, and send access addresses of the target service ends respectively corresponding to the respective first access requests to the core network switch;

The core network switch 402 is further configured to send each first access request to a corresponding target server respectively based on an access address of the target server corresponding to each first access request respectively;

the server 408 is configured to respond to a first access request sent by the core network switch.

Illustratively, the client sends a first access request for the target domain name to the core network switch. The core network switch receives first access requests sent by all clients respectively and sends all the first access requests to domain name resolution equipment.

And after receiving the first access requests, the domain name resolution equipment processes the first access requests corresponding to the same domain name. Specifically, for each first access request corresponding to the target domain name, resource occupation information corresponding to each first access request corresponding to the target domain name is obtained, and when each first access request is determined to be uniformly distributed to each service end corresponding to the target domain name, the service ends respectively correspond to expected resource occupation rates. And according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same service end, adjusting initial load balancing parameters corresponding to the service ends corresponding to the target domain name respectively to obtain target load balancing parameters corresponding to the service ends corresponding to the target domain name respectively. And determining target service ends corresponding to the first access requests aiming at the target domain name based on the target load balancing parameters corresponding to the service ends respectively, and sending the access addresses corresponding to the first access requests to the core network switch.

The core network switch sends the first access request to the corresponding target server based on the access address of the target server corresponding to the first access request returned by the domain name resolution device.

When the server receives a first access request sent by the core network switch, responding to the first access request, generating a corresponding response data packet, and sending the response data packet to a client corresponding to the first access request through the core network switch.

It may be appreciated that the access request processing procedure of the domain name resolution device may refer to the content of each embodiment in the foregoing access request processing method, which is not described herein again.

In the access request processing system, the core network switch sends the received first access request to the domain name resolution device, the domain name resolution device determines the expected resource occupancy rates corresponding to the service ends corresponding to the target domain name respectively based on the first access requests for the target domain name sent by the core network switch, the initial load balancing parameters corresponding to the service ends are adjusted according to the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service ends to obtain target load balancing parameters, the first access requests corresponding to the target domain name are distributed based on the target load balancing parameters, the purpose of timely adjusting the load balancing parameters according to the current actual load conditions of the service ends is achieved, the access requests are distributed according to the load balancing parameters updated in real time, and therefore the resource loads of the service ends corresponding to the same domain name are more balanced, the processing efficiency of the access requests is improved, and the response speed of the service ends to the first access requests sent by the client is improved.

In one embodiment, a domain name resolution device includes a routing policy component and a task scheduling component; the routing strategy component is used for determining a target load balancing parameter corresponding to the server and determining a target server corresponding to the access request; the task scheduling component is used for detecting the working state of each server, and when detecting that a fault server exists, determining an update server corresponding to an access request to be scheduled corresponding to the fault server and establishing a call task aiming at the fault server;

the server side comprises a broadcasting component, a load detection component and an emergency communication component; the broadcasting component is used for sending an emergency communication request to the core network switch when the emergency communication component detects the fault of the domain name resolution equipment; the load detection component is used for acquiring the current resource occupancy rate corresponding to the server; the emergency communication component is used for sending the current resource occupancy rate corresponding to the server to the routing strategy component and monitoring the working state of the domain name resolution equipment;

the client comprises a domain name resolution component; the domain name resolution component is used for extracting domain name resolution information corresponding to the target domain name from a locally cached access path of a first access request aiming at the target domain name and having successful access if the target domain name is accessed when the domain name resolution equipment fails, and sending a second access request carrying the domain name resolution information corresponding to the target domain name to the core network switch;

The core network switch is further configured to send, when receiving the emergency communication request sent by the broadcast component, a second access request carrying domain name resolution information corresponding to the target domain name sent by the client to a server indicated by the domain name resolution information.

Illustratively, a load detection component in the server monitors the current resource occupancy rate of the server in real time and forwards the current resource occupancy rate to an emergency communication component, which sends the current resource occupancy rate to a routing policy component in the domain name resolution device. The routing policy component in the domain name resolution device adjusts initial load balancing parameters corresponding to the server to obtain target load balancing parameters based on the occupancy rate difference between the expected resource occupancy rate and the current resource occupancy rate corresponding to the same server, further determines target server corresponding to each access request corresponding to the domain name based on the target load balancing parameters corresponding to each server corresponding to the same domain name, and sends the access address of the target server corresponding to the access request to the core network switch.

The task scheduling component in the domain name resolution equipment detects the working state of each server in real time, when detecting that a fault server exists, determines an update server corresponding to an access request to be scheduled corresponding to the fault server from the rest normal servers based on the current resource occupancy rate corresponding to the server, and sends an access address of the update server corresponding to the access request to be scheduled to a core network switch, so that the core network switch sends the access request to be scheduled to the update server based on the access address corresponding to the update server.

The emergency communication component included in the service end monitors the working state of the domain name resolution equipment, and when the fault of the domain name resolution equipment is monitored, the broadcasting component sends an emergency communication request to the core network switch. The core network switch starts temporary routing when receiving an emergency communication request sent by a broadcasting component of the server. When the client monitors the fault of the domain name resolution equipment, when an access request for a target domain name is sent, a routing path which is successful in the last access and corresponds to a first access request for the target domain name is obtained from a locally cached routing log set through a domain name resolution component, domain name resolution information corresponding to the target domain name is resolved from the routing path, and a second access request carrying domain name resolution information corresponding to the target domain name is sent to a core network switch. After the core network switch starts the temporary route, the core network switch performs the temporary route according to the domain name resolution information carried in the second access request, that is, sends the second access request to the server indicated by the domain name resolution information.

In the above embodiment, the domain name resolution device timely adjusts the initial load balancing parameters corresponding to the server to obtain the target load balancing parameters according to the difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the server, and distributes each access request corresponding to the domain name to the corresponding server based on the target load balancing parameters corresponding to each server corresponding to the same domain name, so that the resource loads corresponding to each server can be timely and effectively adjusted, the resource loads corresponding to each server are more balanced, and the processing efficiency of the access request is improved. Meanwhile, when the domain name resolution device detects that a fault server exists in each server corresponding to the target domain name, the to-be-scheduled access request corresponding to the fault server is distributed to the normal server with the lowest current resource occupancy rate based on the current resource occupancy rates respectively corresponding to the normal servers corresponding to the target domain name, so that the to-be-scheduled access request can be responded in time, and the influence of the occurrence of faults of the server on the access request processing efficiency is effectively reduced. In addition, when the domain name resolution equipment is in failure, the core network switch starts temporary routing, and according to domain name resolution information carried in the second access request, the second access request is sent to a server indicated by the domain name resolution information, so that reliability and stability of access request processing are improved.

In a specific embodiment, the access request processing method of the present application may be applied to an access request processing system. For example, as shown in fig. 5, a DNS (Domain Name Server, domain name system) cluster is deployed in the access request processing system, and a routing policy component, a fault scheduling component, and a data synchronization component are deployed in the DNS server, a load detection component, a DNS cache component, and a HOST component (i.e., an emergency communication component), and a broadcast component are deployed in each server, and a HOST device (i.e., a domain name resolution component for resolving a mapping relationship of a domain name and an IP from a DNS cache) is deployed in the client. The access request processing method comprises the following steps:

1. load balancing based on DNS clusters

As shown in fig. 5, the core network switch receives the access request sent by the client, and sends the access request to the DNS master server in the DNS cluster. The routing strategy component in the DNS main server realizes dynamic routing according to the current load data of the servers pushed in real time by the HOST component in each server, namely, task assignment is executed according to the current load balancing parameters respectively corresponding to each server. The data synchronization component in the DNS main server synchronizes data to each backup server in the DNS cluster in real time, and when the DNS main server in the DNS cluster fails, the DNS backup server in the DNS cluster replaces the DNS main server to carry out dynamic routing, so that the stability of dynamic routing is ensured. The DNS cluster sends the IP address of the server side allocated for the access request to the core network switch, and the core network switch sends the access request to the corresponding server side according to the IP address.

2. Service end fault disaster recovery

As shown in fig. 6, when a failed server occurs, for example, when the server has resource load overrun, task scheduling is overtime or task scheduling is refused, the server failure is determined. The routing strategy component is communicated with the task scheduling component and performs temporary scheduling of the current detention access request corresponding to the fault server. The task scheduling component dynamically distributes the reserved access requests according to the current load data (resource pool load condition) pushed by the HOST component in real time in each service end (resource pool) which normally operates, and pushes the reserved access requests to the service end with lower resource load. The task scheduling component establishes task scheduling with the fault server, and calls the fault server in real time until the fault of the server is eliminated.

3. DNS cluster fault disaster recovery

As shown in fig. 7, when the DNS cluster fails, temporary disaster recovery of single point failure of the DNS cluster is achieved within 30 minutes through HOST components in the client and the server. The HOST component in the server communicates with the load balancing routing device in the DNS cluster in real time, and when communication interruption is detected, the broadcasting component informs the core network switch to start temporary routing based on the HOST file. When the client detects a DNS cluster fault, a HOST component in the client starts a temporary fault scheduling strategy, generates a HOST temporary file from a route analysis log of a local DNS cache record, and when an access request is sent to a core network switch, domain name analysis information corresponding to a domain name corresponding to the access request in the HOST temporary file is sent to the core network switch in cooperation with the access request. The core network switch directly sends the access request to a server indicated by the domain name resolution information based on the domain name resolution information carried in the access request. When the server receives an access request carrying domain name resolution information, checking the access request based on a DNS cache, and responding to the access request if a mapping relation between the server IP and the client IP exists in the DNS cache.

In the embodiment, the route intellectualization of the core network is realized, the intelligent route scheduling of signaling and telephone traffic is completed through the real-time load condition fed back by the server, so that the dispatching of the access request/telephone traffic is more intelligent and balanced, the node limit of distributed deployment can be effectively broken through, the node resource is utilized to the maximum extent, the intelligent scheduling in a wider range is realized, the operation efficiency and the customer experience are improved, and the method has stronger practicability and industry universality. In addition, the access request processing method can be applied to the traffic intelligent scheduling and shunting scene of the distributed large-scale call center, combines the development trend of the distributed call center and the current node fault problem, calculates the configuration parameters of dynamic routing adjustment according to the current network communication and the bearing state of each service end, and provides active maintenance intelligent scheduling service in advance from the source of request dispatching. The intelligent routing of signaling, telephone traffic, mobile network data and the like to each bearing node is realized at the core network side, the load balancing and emergency scheduling of each bearing node are realized, and the fault mutual backup capability of the bearing node (namely the service end) is not relied on any more. The method can be realized by adding the related modules and the algorithm strategies in the access layer, is simple and convenient, and has stronger operability.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides an access request processing device for implementing the above related access request processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the access request processing device or devices provided below may refer to the limitation of the access request processing method in the above description, which is not repeated here.

In one embodiment, as shown in fig. 8, there is provided an access request processing apparatus including: an access request receiving module 802, an expected occupancy determining module 804, a load balancing parameter determining module 806, a target server determining module 808, and an access address transmitting module 810, wherein:

an access request receiving module 802, configured to receive a plurality of first access requests for a target domain name sent by a core network switch; the plurality of first access requests are sent by a plurality of clients to the core network switch.

The expected occupancy rate determining module 804 is configured to determine, based on the resource occupancy information corresponding to each first access request, an expected resource occupancy rate of each server corresponding to the target domain name.

The load balancing parameter determining module 806 is configured to adjust initial load balancing parameters corresponding to the server based on an occupancy difference between a current resource occupancy and an expected resource occupancy corresponding to the same server, so as to obtain target load balancing parameters corresponding to each server.

The target server determining module 808 is configured to determine, from each server, a target server corresponding to each first access request, based on target load balancing parameters corresponding to each server.

The access address sending module 810 is configured to send the access addresses of the target service ends corresponding to the first access requests to the core network switch, so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses.

In one embodiment, the load balancing parameter determination module 806 is further configured to:

aiming at any one of the service terminals, based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service terminal, the initial request dispatch proportion and the initial request dispatch interval contained in the initial load balancing parameter corresponding to the service terminal are adjusted to obtain the target request dispatch proportion and the target request dispatch interval corresponding to the service terminal, and the target load balancing parameter corresponding to the service terminal is formed; wherein, the target request dispatch proportion and the occupancy rate difference are in negative correlation, and the target request dispatch interval and the occupancy rate difference are in positive correlation; the target request dispatch proportion is used for indicating the proportion of the first access requests dispatched to the server in each first access request, and the target request dispatch interval is used for indicating the duration of the interval required for dispatching the first access requests to the server.

In one embodiment, as shown in fig. 9, the access request processing apparatus further includes:

the server fault response module 902 is configured to determine, when detecting that a fault server exists in each server corresponding to the target domain name, an updated server corresponding to an access request to be scheduled corresponding to the fault server from the remaining normal servers based on a current resource occupancy rate corresponding to the server; sending an access address of an update server corresponding to the access request to be scheduled to a core network switch, so that the core network switch sends the access request to be scheduled to the update server based on the access address corresponding to the update server; establishing a call task aiming at the fault server until the fault server returns to normal; the calling task is used for acquiring the working state of the fault server.

According to the access request processing device, the expected resource occupancy rates corresponding to the service ends corresponding to the target domain names are estimated based on the resource occupancy rates corresponding to the first access requests corresponding to the target domain names, the initial load balancing parameters corresponding to the service ends are adjusted according to the occupancy rate difference between the current resource occupancy rates corresponding to the service ends and the expected resource occupancy rates to obtain the target load balancing parameters, and the first access requests corresponding to the target domain names are distributed based on the target load balancing parameters, so that the load balancing parameters are timely adjusted according to the current actual load conditions of the service ends, the access requests are distributed according to the load balancing parameters updated in real time, the resource loads of the service ends can be more balanced, and the access request processing efficiency is improved.

The respective modules in the above-described access request processing apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 10. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured 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, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing the data such as the resource occupation information, the resource occupation rate and the like. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of processing an access request.

It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.

In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-described method embodiments.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. An access request processing method, applied to a domain name resolution device, comprising:

receiving a plurality of first access requests aiming at a target domain name, which are sent by a core network switch; the plurality of first access requests are sent to the core network switch by a plurality of clients;

determining respective expected resource occupancy rates of the service ends corresponding to the target domain name based on the resource occupancy information corresponding to the first access requests;

Based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server, adjusting initial load balancing parameters corresponding to the server to obtain target load balancing parameters corresponding to the server respectively;

determining target service ends corresponding to the first access requests respectively from the service ends based on the target load balancing parameters corresponding to the service ends respectively;

2. The method of claim 1, wherein the adjusting initial load balancing parameters corresponding to the server based on the occupancy difference between the current occupancy of resources and the expected occupancy of resources corresponding to the same server, to obtain target load balancing parameters corresponding to the respective server, includes:

aiming at any one of the service terminals, based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the service terminal, adjusting the initial request dispatch proportion and the initial request dispatch interval contained in the initial load balancing parameter corresponding to the service terminal to obtain a target request dispatch proportion and a target request dispatch interval corresponding to the service terminal, and forming a target load balancing parameter corresponding to the service terminal;

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

when detecting that a fault server exists in each server corresponding to the target domain name, determining an update server corresponding to an access request to be scheduled and corresponding to the fault server from the rest normal servers based on the current resource occupancy rate corresponding to the server;

sending an access address of an update server corresponding to the access request to be scheduled to the core network switch, so that the core network switch sends the access request to be scheduled to the update server based on the access address corresponding to the update server;

establishing a call task aiming at the fault server until the fault server returns to normal; the call task is used for acquiring the working state of the fault server.

4. The method according to claim 1, wherein the core network switch is further configured to, when receiving an emergency communication request sent by a server corresponding to the target domain name, send a second access request sent by a client and carrying domain name resolution information corresponding to the target domain name to the server indicated by the domain name resolution information;

the emergency communication request is sent when the domain name resolution device fails, the second access request is sent when the domain name resolution device fails, and the domain name resolution information is cached locally by the client based on the access path of the first access request that is successfully accessed.

5. An access request processing system, wherein the system comprises a core network switch, a domain name resolution device, a plurality of clients, and a plurality of servers:

the client is used for sending a first access request aiming at a target domain name to the core network switch;

the core network switch is configured to receive first access requests sent by a plurality of clients respectively, and send each first access request to the domain name resolution device;

the domain name resolution device is configured to determine, based on resource occupancy information corresponding to each first access request, respective expected resource occupancy of each server corresponding to the target domain name, adjust initial load balancing parameters corresponding to the server based on an occupancy difference between a current resource occupancy and an expected resource occupancy corresponding to the same server, obtain target load balancing parameters corresponding to each server, determine, based on the target load balancing parameters corresponding to each server, target servers corresponding to each first access request from each server, and send access addresses of the target servers corresponding to each first access request to the core network switch;

The core network switch is further configured to send each first access request to a corresponding target server respectively based on an access address of the target server corresponding to each first access request respectively;

the server is configured to respond to a first access request sent by the core network switch.

6. The system of claim 5, wherein the domain name resolution device comprises a routing policy component and a task scheduling component; the routing strategy component is used for determining a target load balancing parameter corresponding to the server and determining a target server corresponding to the access request; the task scheduling component is used for detecting the working state of each server, and when detecting that a fault server exists, determining an update server corresponding to an access request to be scheduled and corresponding to the fault server, and establishing a call task aiming at the fault server;

the server comprises a broadcasting component, a load detection component and an emergency communication component; the broadcasting component is used for sending an emergency communication request to the core network switch when the emergency communication component detects the fault of the domain name resolution equipment; the load detection component is used for acquiring the current resource occupancy rate corresponding to the server; the emergency communication component is used for sending the current resource occupancy rate corresponding to the server to the routing strategy component and monitoring the working state of the domain name resolution equipment;

The client comprises a domain name resolution component; the domain name resolution component is configured to extract domain name resolution information corresponding to the target domain name from a locally cached access path of a first access request for the target domain name, where the first access request is successful, if the target domain name is accessed when the domain name resolution device fails, and send a second access request carrying domain name resolution information corresponding to the target domain name to the core network switch;

7. An access request processing apparatus, the apparatus comprising:

the access request receiving module is used for receiving a plurality of first access requests aiming at the target domain name and sent by the core network switch; the plurality of first access requests are sent to the core network switch by a plurality of clients;

The load balancing parameter determining module is used for adjusting initial load balancing parameters corresponding to the server side based on the occupancy rate difference between the current resource occupancy rate and the expected resource occupancy rate corresponding to the same server side to respectively obtain target load balancing parameters corresponding to each server side;

the target server determining module is used for determining target servers corresponding to the first access requests respectively from the servers based on the target load balancing parameters corresponding to the servers respectively;

and the access address sending module is used for sending the access addresses of the target service ends corresponding to the first access requests to the core network switch so that the core network switch sends the first access requests to the corresponding target service ends based on the access addresses.

8. 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 of claims 1 to 4 when the computer program is executed.

9. 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 4.

10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any of claims 1 to 4.