Thanks! But what if the jobs get killed or failed? Does hadoop try to clean it? we are considering bad situations - if job gets killed, will the tmp dirs sit on local disks forever and eats up all the diskspace?
I guess this should be considered in distributed cache, but those files are read-only, and our program will generate new temporary files. --Q On Mon, Jun 22, 2009 at 4:19 PM, Pankil Doshi <forpan...@gmail.com> wrote: > Yes, If your job gets completed successfully .possibly it removes after > completion of both map and reduce tasks. > > Pankil > > On Mon, Jun 22, 2009 at 3:15 PM, Qin Gao <q...@cs.cmu.edu> wrote: > > > Hi All, > > > > Do you know if the tmp directory on every map/reduce task will be deleted > > automatically after the map task finishes or will do I have to delete > them? > > > > I mean the tmp directory that automatically created by on current > > directory. > > > > Thanks a lot > > --Q > > >
