mapred.tasktracker.map.tasks.maximum: how many map tasks can be run concurrently on a map-reduce slave node.
mapred.tasktracker.reduce.tasks.maximum: how many reduce tasks can be run concurrently on a map-reduce slave node. mapred.reduce.tasks: how many reduce task for a specific job. mapred.map.tasks: how many map task for a specific job. Note that this configuration is just a lint. On Tue, Nov 16, 2010 at 11:20 AM, Wei Xue <simonxu...@gmail.com> wrote: > I depends on how many tasks you created, how many slave nodes in the > cluster, how many slots allocated in each slave node, and how each node is > occupied. Each of them has corresponding setting parameters. Please refer to > hadoop document for more details. > > 2010/11/16 Shen LI <geminialex...@gmail.com> > > How to set the number of tasks running on each slave? (e.g., 4 tasks on >> each slave node) >> >> Thanks >> > > -- Jingguo
