Actually, that is configurable. Multiple tasks can be run from the same JVM, and you can also use the MultithreadedMapper (http://hadoop.apache.org/mapreduce/docs/r0.21.0/api/org/apache/hadoop/mapreduce/lib/map/MultithreadedMapper.html) to at least make map tasks run in the same thread.
On Tue, Mar 1, 2011 at 9:09 AM, Harsh J <qwertyman...@gmail.com> wrote: > Hello, > > On Tue, Mar 1, 2011 at 7:29 PM, bikash sharma <sharmabiks...@gmail.com> wrote: >> Hi, >> As a follow-up question, do map/reduce tasks run as threads or processes? > > Every launched Task runs as an independent process, communicating over > a network interface (lo) with the TaskTracker for reporting/etc. > purposes. > > -- > Harsh J > www.harshj.com > -- Chris
