Hi all,
I am a newbie to hadoop, and am setting up a multi-node cluster. I have
a trivial question on the HDFS. In the hadoop doc it has a diagram
showing the client performs a read/write to the dfs, but it isn't clear
to me on how the client will be setup. I assume you will have to
install the hadoop binaries, and connect to the namenode (master) to
access the dfs, like this:
# ./hadoop dfs -fs hdfs://<master-hostname>:9000 -ls /
I need to do benchmark on create/read/write operations on hadoop dfs.
Any pointers appreciated. Thanks in advance!
-Yun
