1

I have only one Data Node on my dev environment on EC2. I ran heavy MR job and in 6 hours noticed that 100% of mappers and 20% of reducers finished (1 of reducer shows 100% competition, other ones - 0%). Looks like job is hung between 2 reducer runs. I don't see any errors in log files.

What it can be?

P.S. Last logs of successfully finished reducer:

2012-11-09 11:29:21,576 INFO org.apache.hadoop.mapred.Task: Task:attempt_201211090523_0004_r_000000_0 is done. And is in the process of commiting
2012-11-09 11:29:22,692 INFO org.apache.hadoop.mapred.Task: Task attempt_201211090523_0004_r_000000_0 is allowed to commit now
2012-11-09 11:29:22,719 INFO org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter: Saved output of task 'attempt_201211090523_0004_r_000000_0' to /data/output/1352457275873/20121109-053433-common
2012-11-09 11:29:22,721 INFO org.apache.hadoop.mapred.Task: Task 'attempt_201211090523_0004_r_000000_0' done.
2012-11-09 11:29:22,725 INFO org.apache.hadoop.mapred.TaskLogsTruncater: Initializing logs' truncater with mapRetainSize=-1 and reduceRetainSize=-1
Marboni
  • 111
  • 4

1 Answers1

0

JobTracker log contains following warning message:

2012-11-10 00:00:01,911 WARN org.apache.hadoop.mapred.JobInProgress: No room for reduce task. Node tracker_p-10-0-0-148.liveperson.com:localhost.localdomain/127.0.0.1:35533 has 71983820800 bytes free; but we expect reduce input to take 98282873836

Not enough disk space for job execution. Solved after increasing of free space.

Marboni
  • 111
  • 4