Efficient Job Execution for Map Reduce Using Phase-Level Scheduling Algorithm.

Abstract

Technology’s role in society today has a major impact on our overall sense of living and that
is why in the 21st century, it is offered as a subject. The fast and improved speed of computer systems are
making humans life easier and giving him new opportunity to create an impossible. To improve the
processing speed of systems different technologies are now used like distributed system, parallel
computing. The map reduce which is used in parallel computing is one of the popular data model for
high speed computation in computation technology. The Existing map reduce focuses on scheduling at
the task-level. But unfortunately, the task-level scheduling leads to inefficient job schedules with low
resource utilization and long job execution time.
In this concept we divide the tasks into unequal parts called as phases and apply phase-level scheduling
to these phases and achieve efficient resource usage. In this paper, we present a Scheduler, a Phase and
Resource Information-aware Scheduler for MapReduce clusters that performs resource-aware
scheduling at the level of task phases. Specifically, we show that for most MapReduce applications, the
run-time task resource consumption can vary significantly from phase to phase. Therefore, by
considering the resource demand at the phase level, it is possible for the scheduler to achieve higher
degrees of parallelism while avoiding resource contention.