期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
期号：ICMEET
页码：458
出版社：S&S Publications
摘要：Distributed file systems are key building blocks for cloud computing applications based on the MapReduce programming. In such file systems, nodes simultaneously serve computing and storage functions. Files can alsobe dynamically created, deleted, and appended. This results in load imbalance in a distributed file system. The filechunks are not distributed as uniformly as possible among the nodes. In existing we use round robin algorithm, due tothis algorithm the load balance happens to the server good with some extend. All the servers should response in sametime duration to complete the task.If any one of the server makes delay in response for the given task which impact theCPU computing resource. As a result it can be a bottleneck resource and a single point of failure. Our target is tooptimize the computing resource (server), maximum throughput of servers, to avoid overload or crash of computingservers and to increase the response time. In our system DHT algorithm in such a way to make optimize computingresource and increase response time. In our model we divided the total bytes in to number of active servers and fed thesame accordingly. This will make the effective utilization of the servers. And also we are divided the each file in tonumber of chunks for easy processing which increase the response time as well as easy error re-transmission if any datawas dropped during transmission. Additionally, we aim to reduce network traffic or movement cost caused byrebalancing the loads of nodes as much as possible to maximize the network bandwidth available to normalapplications.
关键词：Load balance; distributed file systems; clouds; Distributed file system
