Data processing method, device, medium and system

Abstract

The invention relates to a data processing method, device, medium and system. The data processing method comprises the steps of: enabling a first business server to receive a URL request; determining a target server based on the URL of each request; when the target server is the first service server, enabling the first service server to respond to the request; and when the target server is not the first service server, forwarding the URL request to the target server. Only one cache file needs to be stored in the node, space occupation is reduced, a bottom layer CPU is consumed for kernel calculation, and the method is not limited by the performance bottleneck of an application layer. Forwarding balance can be achieved for all request types, and the method is wide in application.

Description

technical field [0001] This article relates to a content distribution network, in particular to a data processing method, device, medium and system. Background technique [0002] The CDN system serves as a platform for carrying customer traffic. The server processes customer requests and gives response results. The response consumption speed of the server processing different services is different, which is easy to cause business accumulation. In related technologies, the load balancing method has two disadvantages. One is that the backend requests are directly weighted on the load balancing server, which cannot guarantee cache reuse and cannot maintain keep-alive persistent links for special URLs. The second is to change the hotspot URL strategy to be directly distributed to each cache server by discovering hotspot URLs. However, when domain name requests burst out as a whole and there are no obvious URL hotspots, it will be difficult, because the hotspot discovery system m...

AI Technical Summary

Problems solved by technology

[0002] The CDN system serves as a platform for carrying customer traffic. The server processes customer requests and gives response results. The response consumption speed of the server processing different services is different, which is easy to cause business accumulation.

In related technologies, the load balancing method has two disadvantages. One is that the backend request is directly weighted on the load balancing server, which cannot guarantee cache reuse and cannot maintain the keep-alive persistent link of the special URL.

The second is to change the hotspot URL strategy to be directly distributed to each cache server by discovering hotspot URLs. However, when domain name requests burst out as a whole and there are no obvious URL hotspots, it will be difficult, because the hotspot discovery system mainly modifies the hash method for a single URL hotspot. Diffusion, unable to identify hotspots at the domain name level, let alone handle them

In addition, the existing technology directly calculates the back-end server CPU, disk and other hardware information as the allocation weight, so it is difficult to ensure that special services are concentrated on the same service processor

Secondly, the carrying capacity of the server changes in real time when it is running. If the weight is modified at any time, the cache will not be able to be continuously utilized, resulting in a large number of back-to-source requests, which cannot be tolerated by CDN services.

Images