[HADOOP-3915] reducers hang, jobtracker loosing completely track of them.

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Incomplete
• Affects Version/s: 0.17.1

Environment

EC2, Debian Etch (but not the ec2-contrib stuff)
streaming.jar

• Assignee: Unassigned
• Reporter: Andreas Kostyrka
• Created: 07/Aug/08 06:15
• Updated: 18/Jul/14 20:49
• Resolved: 18/Jul/14 20:49

Description

I just noticed the following curious situation:

-) 18 of 22 reducers are waiting for 3 hours or so with 0.01MB/s and no progress.
-) hadoop job -kill-task does not work on the ids shown
-) killing all reduce work tasks (the spawned Python processes, not java TaskTracker$Child) gets completely ignored by the JobTracker, the jobtracker shows them still as running.

Issue Links

• relates to: HADOOP-3155 reducers stuck at shuffling