![]() | Only 14 pages are availabe for public view |
Abstract MapReduce is a programming model for processing large distributed data in parallel. Hadoop is a popular MapReduce implementation that has got a wide popularity in research and industry. Most of current Hadoop schedulers consider the homogeneity of the resources on which Hadoop is running and assign each node a fixed number of slots over the run time neglecting the different nodes computing capabilities and the node performance over the run time. from the experimental tests, it was found that this assumption leads to under or over utilization of resources. For that, we propose a new Hadoop scheduler that overcomes some of the drawbacks of the current Hadoop schedulers. |