hadoop cluster: map task run only on one machine and not all

Question

I have a hadoop cluster of three machines where one machine acts as both master and slave.

When I run wordcount-example, it run map tasks on two machines - worker1 and worker2. But when I run my own code, it runs only on one machine - worker1, how can I make map tasks run on all machines?

Input Split Locations

/default-rack/master
/default-rack/worker1
/default-rack/worker2  

FIXED!!!

I added the following in my configuration of mapred-site.xml and it fixed it

<property>
  <name>mapred.map.tasks</name>
  <value>100</value>
</property>

Answer 1

How big is your input? Hadoop splits up the jobs into input splits, and if your file is too small, it will only have one split.

Try a larger file-- say around 1GB in size and see how mappers you get then.

---

You can also check to make sure that every TaskTracker is reporting properly to the JobTracker. If there is a TaskTracker that is not properly connected, it will not get tasks:

   $ hadoop job -list-active-trackers

This command should output all 3 of your hosts.