You are viewing a plain text version of this content. The canonical link for it is here.

Posted to mapreduce-issues@hadoop.apache.org by "zhaoyunjiong (JIRA)" <ji...@apache.org> on 2014/01/07 14:17:51 UTC

[jira] [Created] (MAPREDUCE-5711) When JobTracker writing JobHistory to HDFS, it may hung for long time due to DataNode error

zhaoyunjiong created MAPREDUCE-5711:
---------------------------------------

             Summary: When JobTracker writing JobHistory to HDFS, it may hung for long time due to DataNode error
                 Key: MAPREDUCE-5711
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5711
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
    Affects Versions: 1.2.0
            Reporter: zhaoyunjiong
            Assignee: zhaoyunjiong
             Fix For: 1.2.2


When writing JobHistory to HDFS, it may takes very long time due to DataNode error, unfortunately, it also hold JobTracker lock, so it makes JobTracker hung for long time. It happens couple of times on our cluster.



--
This message was sent by Atlassian JIRA
(v6.1.5#6160)