Straggler handling approaches in mapreduce framework: a comparative study

The proliferation of information technology produces a huge amount data called big that cannot be processed by traditional database systems. These Various types come from different sources. However, stragglers are major bottleneck in processing, and hence the early detection accurate identification can have important impacts on performance processing. This work aims to assess five methods: Hadoop native scheduler, LATE Scheduler, Mantri, MonTool, Dolly. these techniques was evaluated based three benchmarked Sort, Grep WordCount. results show Scheduler performs best it would efficient obtain better for identification.