• S.Vijayarangam
• J.Sasirekha
• J.Megalai
• N.Kalpana

MapReduce is programming tool for Hadoop clusters. During the allocation of resources, MapReduce has two levels:-task level and development stage-plane. These steps should be used to verify the performance of individual jobs. There is a limitation with allocation of resources at the operation level. Thus, data locality affects a particular job. We present algorithm called PRISM: presenting at the development stage level. It is called as a development stage-level scheduling. In the development stage-plane, if we want to schedule a job for the given different resource requirements. So here we find that, PRISM achieved data locality in the plurality of clusters. This scheduling algorithm improves the performance of a server that is connected to many nodes; it is also called as a parallelism, and also improves the resource consumption with respect to time. This algorithm is applicable only in the term of Hadoop Scheduler.

Cloud Computing, MapReduce, Hadoop, Scheduling, Resource Allocation

"PRISM: IMPROVING THE SCALABILITY USING DISTRIBUTED SCHEDULERS FOR MAPREDUCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.569-571, September-2018, Available :http://www.jetir.org/papers/JETIR1809116.pdf

"PRISM: IMPROVING THE SCALABILITY USING DISTRIBUTED SCHEDULERS FOR MAPREDUCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp569-571, September-2018, Available at : http://www.jetir.org/papers/JETIR1809116.pdf