Forwarding method and transmission method for cache request, and related devices

Abstract

Embodiments of the invention relate to the technical field of communications, and disclose a forwarding method and a transmission method for cache requests, and related devices. In the invention, theforwarding method for a cache request comprises the following steps: obtaining a first cache request transmitted by a client; determining, according to the first cache request, a first cache instancecorresponding to the first cache request; and determining whether to transmit the first cache request to the first cache instance according to the state of the first cache instance. In this implementation, the proxy instance can determine the processing manner of the cache request according to the state of the cache instance, which avoids a large number of cache requests breaking through the cacheinstance and directly reaching the database, resulting in a crash of the cache system.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of communications, and in particular, to a cache request forwarding method, transmission method, and related devices. Background technique [0002] Caching technology is widely used in Internet applications, such as websites, application programs (Application, APP) or cloud computing platforms. Using caching technology can effectively improve the throughput of the application, improve the response speed of the application, and allow limited resources to serve more customers. Taking the Linux system as an example, a typical cache application on the Linux system, such as the cache system memcache, generally starts one or more cache processes on each cache server, and each process is a separate cache instance. are generally unrelated. At present, the mainstream high-availability cache technology is to realize the client's reading of cached data by directly connecting the client to th...

AI Technical Summary

Problems solved by technology

[0003] However, the inventors found that there are at least the following problems in the prior art: the way that the client directly connects to the cache instance is relatively simple to implement, but the response of the application may become slow, and even cache breakdown may occur, resulting in the entire Cache system crashes

In use, it often happens that a cache instance hangs up, but the client will still forward the cache request to the cache instance until the cache request times out, which will cause the response of the entire system to become very slow

Moreover, some services of the cloud computing platform rely on session control session technology. Session technology is generally cached in the cache. If the caches are independent of each other, it must be ensured that the corresponding client accesses the corresponding cache server. This requires load balancing Layer expansion will bring great trouble to the expansion of the cache system and the replacement of faulty nodes

Images