Hadoop is a framework for processing large amount of data in parallel. It uses the Hadoop Distributed File System (HDFS) and MapReduce framework for processing. Job scheduling is an important process in Hadoop MapReduce. There are three types of schedulers mainly used in Hadoop Framework. They are namely FIFO, Fair and Capacity Scheduler. In Hadoop Framework the schedulers are a pluggable component now a day. There are jobs which have dependency on an external service like database or web service. This condition will lead to the failure of tasks due to overloading. In this case, Hadoop needs to re-run the entire tasks in another slots. To address this issue, the TaskTracker aware scheduling has been introduced. The TaskTracker scheduler enables users to configure a maximum load per TaskTracker in the Job Configuration itself. If the load of the TaskTracker reaches its maximum limit then the algorithm will not allow the task to run and stops the task from failing. Also, the TaskTracker aware scheduler allows the users to select the TaskTracker per Job which is configured in the Job configuration.
Poornima K S, Akshatha G (2017).
"SCHEDULING WITH TASKTRACKER FOR MAPREDUCE IN HADOOP".
International Journal of Contemporary Research in Computer Science and Technology,
3(7), pp. 1-4.
