Improved load balancing for distributed file system using self acting and adaptive loading data migration process

Abstract

Load balancing in a distributed file system is becoming essential as a distributed file system is gaining more popularity both in use and research. Resource utilization is very much important as it affects the cost of the system, response time, performance etc. Now a days dynamic load balancer is adopted by most of distributed file systems. Adaptive loading data migration and Self acting load balancing proves better performance, which behaves centralized and distributed way respectively. A Modified approach to create new distributed, dynamic load balancer for distributed file system is adopted. In which, the algorithm considers constraints as network load, disk IO load, Disk capacity, load which was not considered in earlier approaches. The load balancing problem is solved based on constraint satisfaction theory, which sets the optimum level so that system throughput, response time is improved. Experimental results show that overall performance is improved by 8 to 9%.