I want to restrict number of simultaneously map tasks running at one slave node.
In my case, when I submit my job, Hadoop generate 8 map tasks, when I looked at Job history UI at port 19888, I always saw that 8 map tasks started at the same time at same slave node.
Even I tried to set this attribute mapreduce.tasktracker.map.tasks.maximum
equal to 4 (from how to restrict the concurrent running map tasks?). It still didn't work for me.
Does anyone have a experiment to deal with this issue?