抽象的

Survey on Load Rebalancing For Distributed File System in Cloud with Security

Jayesh D. Kamble, Prof. Y.B.Gurav

In a Cloud computing, distributed file system is used as a key building block by using map reduce paradigm. In such systems, the node performs different operations like computing as well as storage. In distributed file systems, those different operations are performed on different nodes parallel by partitioning a large file into small chunks.In a cloud computing setting, failure is that the norm and nodes is also upgraded, replaced, and accessorial within the system. Files may get created, deleted, and appended dynamically. This will affect as load imbalance in a distributed file system; it means the file chunks are not distributed as uniformly as possible among the nodes. In cloud, if number of storage nodes, number of files and accesses to that file increases then the central node (master in MapReduce) becomes bottleneck. The load rebalancing task is used to eliminate the load on central node. Using load rebalancing algorithm the load of nodes is balanced as well as the movement cost is reduced. In this survey paper the problem of load imbalancing is overcome. And we are going to consider the security while rebalancing the load of distributed file system as well.