问题
So I have set up a hadoop 2.6.0 cluster and I want to run a benchmark to test read a write throughput. I keep reading places that I can use TestDFSIO to do this, but I am not able to find a way to run this program on Hadoop version 2.6.0. Does anyone know how to run this test, or an alternative?
回答1:
HiBench has an implementation of DFSIO. You can find HiBench by clicking here.
回答2:
You can run TestDFSIO benchmark test in hadoop 2.6.0 by the following command:
$ hadoop jar /usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-client-jobclient-2.6.0-tests.jar TestDFSIO -write -nrFiles 10 -fileSize 100
For detailed description you can also visit http://researchbyomesh.blogspot.in/2015/12/running-benchmark-tests-in-hadoop.html
来源：https://stackoverflow.com/questions/27324972/hadoop-2-6-0-testdfsio-benchmark