So why it's called hadoop streaming, if it doesn't behave like a
streaming application (The reduces don't receive data as long as it is
produced by the map tasks)?
On 16 January 2013 05:41, Jeff Bean <[EMAIL PROTECTED]> wrote:
> me property. The reduce method is not called until the mappers are done, and
> the reducers are not scheduled before the threshold set by
> mapred.reduce.slowstart.completed.maps is reached.