A novel algorithm of load balancing in distributed file system for cloud

摘要

Distributed file systems are building blocks for cloud computing. Here, nodes simultaneously serve computing and storage functions. File is partitioned into number of chunks allocated with distinct nodes so that tasks can be performed in parallel over the nodes. In a cloud computing environment, failure can occur, and nodes can be upgraded, replaced, and added to the system. Files can be dynamically created, deleted, or appended, that results in load imbalance in the distributed file system. Emerging distributed file systems in production systems strongly depend on a central node for chunk reallocation. The dependence is clearly inadequate in large-scale environment because the central load balancer is put under considerable workload that is linearly scaled with the system size, and thus leads to performance bottleneck and the single point of failure. Here in this paper, a fully distributed load balancing algorithm is presented to cope with the load imbalance problem.