three jobs in my hadoop cluster have stopped at state 4 for five hours!!!
my hadoop become more and more slow sice i begin setup it, i think mybe
because the hadoop filesystem become more and more
larger? here is bin/hadoop fs -count result:
401141 824522 659714994647 hdfs://hadoop01:9000/user/hadoop
things become very bad since three days ago when i begin runing five more
jobs simultaneously. a job need two minutes now need
eight more minutes, and i noticed that the jobs submited to hadoop stay at
state 4 in the job queue for long time, about one minute and more.
now , three jobs stay at state 4 for five hours because the last completed
job finished at five hours ago!
here is the bin/hadoop job -list result:
3 jobs currently running
JobId State StartTime UserName Priority
SchedulingInfo
job_201001221137_7050 4 1264453449856 hadoop NORMAL
job_201001221137_7051 4 1264453919364 hadoop NORMAL
job_201001221137_7052 4 1264453927418 hadoop NORMAL
can any body help me?
--
Regards
Junyong
