You are viewing a plain text version of this content. The canonical link for it is here.

Posted to common-dev@hadoop.apache.org by Stefan Groschupf <sg...@media-style.com> on 2006/02/21 23:19:44 UTC

partitions

Hi,
is it possible by a hack / or is planed to implement to support  
tasktracker network partitions.
What I'm interested in, is to group a set of tasktrackers together in  
a group called 'muchMemory' and run a mapred job only on  
trasktrackers of this group.
May partition is the wrong word since this term is already used to  
described something different in hadoop.
May called it subnet's or tasktracker groups.

Any thoughts?
Thanks.
Stefan

---------------------------------------------
blog: http://www.find23.org
company: http://www.media-style.com