Elastic cloud distributed massive request processing method, device and system

Abstract

The invention provides an elastic cloud distributed massive request processing method, device and system, and can instantaneously and automatically carry out expansion when a server cannot respond to a peak value. The method comprises the steps that: S1: a cloud computing management platform creates a container, and a message queue cluster, a ZooKeeper cluster, a service instance and a data storage cluster are respectively constructed on the container; S2: a client sends requests containing time to a load balancing server, the load balancing server distributes the requests to the message queue cluster, and after being synchronized by the ZooKeeper cluster, the requests are rearranged according to a time sequence; S3: the service instance acquires the requests from the message queue cluster, processes the requests, then stores a processing result to the data storage cluster, and returns the processing result to the client; and in the process of S1 to S3, the cloud computing management platform monitors a state of the container where the service instance is positioned, and when a state index exceeds a preset threshold, a new container is created by duplicating the container so as to improve a processing speed.

Description

technical field [0001] The present invention relates to the field of computer technology and software, in particular to a method, device and system for elastic cloud distributed mass request processing. Background technique [0002] With the continuous development of Internet technology, the number of requests initiated by the client has shown a massive increase. This phenomenon is more prominent in the field of e-commerce, especially when merchants carry out various promotional activities. Therefore, timely processing of massive requests is particularly important. Because massive network requests are like blood clots, once a bottleneck is encountered, the entire blood vessel will be blocked. [0003] In order to respond to massive requests in a timely manner, it is usually necessary to use clustering and load balancing technologies; in order to understand the sequence of requests, the request time must be known, and user requests are generally processed through a request q...

AI Technical Summary

Problems solved by technology

However, the above existing technologies cannot support dynamic expansion

Once a problem occurs, server operation and maintenance personnel need to increase the number of servers in time, restart the service, etc., which will take a long time, and the complexity and uncertainty of the process will bring greater risks to request processing; in addition, the existing scheme It does not consider the fairness of user request time processing. Generally, the time when the request reaches the server is the request start time, which is not fair to the request initiator.

Images