一种基于流媒体压缩算法的高性能集群监控系统  

CLUSTER MONITORING SYSTEM WITH HIGH PERFORMANCE BASED ON STREAMING MEDIA COMPRESS ALGORITHM

作　　者：樊书华 王鹏[2] 汪卫[2] Fan Shuhua;Wang Peng;Wang Wei(School of Software,Fudan University,Shanghai 201203,China;School of Computer Science,Fudan University,Shanghai 200433,China)

机构地区：[1]复旦大学软件学院,上海201203 [2]复旦大学计算机科学技术学院,上海200433

出　　处：《计算机应用与软件》2019年第11期25-31,50,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(U1509213);上海市软件和集成电路产业发展专项项目(170512)

摘　　要：随着计算机集群规模与数据量迅速增加,集群监控系统逐渐成为近几年来的研究热点。集群管理员 通过对集群中各项指标进行监控采集,有针对性地采取相应措施,有力地保证了系统的稳健运行。然而传统集群 监控系统往往面临海量数据产生的性能瓶颈,为此设计并实现一种基于流媒体压缩算法的高性能集群监控系统。 通过对产生性能问题的原因进行分析,提出并实现数据帧冗余性优化算法,同时把部分计算量从服务器端移到客 户端。通过系统实验以及与目前主流算法进行对比,证明该系统对实际性能产生有效的提升与优化。With the explosive growth of cluster scale and data volume,research about cluster monitoring system has become a hot topic in recent years.Cluster administrators monitor and collect various indicators in the cluster,and take corresponding measures to effectively ensure the stable operation of the system.However,there are bottlenecks in the traditional monitoring system with the increasing amount of data.Therefore,we design and implement a cluster monitoring system with high performance based on streaming media compress algorithm.Through the analysis of the causes of performance problems,an optimization algorithm for data frame redundancy was proposed and implemented.And some computational load was shifted from the server side to the client side.Through system experiments and comparison with the current mainstream algorithms,it is proved that the actual performance can be effectively improved and optimized.

关 键 词：集群监控 流媒体压缩算法 数据帧冗余性优化 系数量化 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]