reduce hangs after applying HADOOP-248 on 20 node cluster
---------------------------------------------------------
Key: HADOOP-949
URL: https://issues.apache.org/jira/browse/HADOOP-949
Project: Hadoop
Issue Type: Bug
Components: mapred
Affects Versions: 0.10.1
Reporter: Nigel Daley
Assigned To: Owen O'Malley
After HADOOP-248 was committed, my benchmarks started to hang. Running
TestDFSIO on 20 nodes, the job's single reduce is hanging. Annodated logs from
the task tracker running the reduce are included in the next comment. I have
reverted the patch using:
cd $trunk_dir
svn merge -r 500410:500397 .
and reran some benchmarks. They all pass.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
