High Performance and High Availability Archived Stream System for Big Data

Abstract

The increasing number of applications for large data, such as Web search engines, we need to have high availability 7*24 tracking, storage and analysis of a large number of real-time user access logs. Traditional common trading application high availability solution, always not efficient enough to store this high-rate only inserted into the archive stream. This paper presents an integrated approach to save of this archive of data streams in a database cluster and rapid recovery. This method is based on a simple replication protocol and high performance data loading and query strategy. Experimental results show that our approach can reach efficient data loading and query and get shorter recovery time than the traditional database cluster recovery methods.