Hadoop Tutorials and Extra Features
See the following commands and tutorials to learn how to test IO speed, debug and profile, do log file performance analysis, and more.
How-tos
Test IO speed
Use the following command to test IO speed.
hadoop jar /usr/lib/hadoop/hadoop-test-0.20.2+737.jar TestDFSIO -write -nrFiles 1 -fileSize 2000
Tutorials
Debugging and profiling with IsolationRunner
See:Â https://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#IsolationRunner
Vaidya log file performance analysis
See:Â https://hadoop.apache.org/docs/r1.2.1/vaidya.html
Profiling
See:Â http://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#Profiling
Debug scripts
See:Â http://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#Debugging
Features
The distributed cache
See:Â http://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#DistributedCache
The HDFS rebalancing feature
See:Â http://hadoop.apache.org/docs/r1.2.1/hdfs_user_guide.html#Rebalancer