You should be able to add nodes to the cluster while jobs are running the jobtracker should start assigning task to the tasktrackers and dfs should start using the nodes for storage

But map data files are stored on the slaves and copied to the reduce task so if a node goes down during a MR job then the maps will have to be ran again.

Billy

"Francois Berenger" <[EMAIL PROTECTED]> wrote in message news:[EMAIL PROTECTED]
Hello,

Is this possible to add slaves with IP address not known in advance
to an Hadoop cluster while a computation is going on?

And the reverse capability: is it possible to cleanly permanently
remove a slave node from the hadoop cluster?

Thank you,
François.



Reply via email to