Improving Current Hadoop MapReduce Workflow and Performance

This study proposes an improvement andimplementation of enhanced Hadoop MapReduce workflow that develop the performance of the current Hadoop MapReduce. This architecture speeds up the process of manipulating BigData by enhancing different parameters in the processing jobs. BigData needs to be divided into many datasets or blocks and distributed to many nodes within the cluster. Thus, tasks can access these blocks in parallel mode and be processed easily. However, accessing the same datasets each time the job is executed causes data overloading problem, so we developed the current MapReduce workflow to improve the performance in terms of data size that is read in the relative jobs.This work uses a bioinformatics DNA datasets to implement the solution