[
https://issues.apache.org/jira/browse/MAPREDUCE-279?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13002947#comment-13002947
]
Lianhui Wang commented on MAPREDUCE-279:
----------------------------------------
i think that the MR2.0 may resolve the thing:
JT doesnot monitor the status of the every job and tasks,because many TT must
RPC to the one JT every few seconds.
and many clients get the job's status through rpc the one JT every few seconds.
so the majority nodes of the cluster connect to the JT discontinuously,that
lead to degrade the performance of the JT.especially the number of cluster
increase,example 10K.
like hdfs's Federation Branch， the MR project must create a new branch for the
2.0.
> Map-Reduce 2.0
> --------------
>
> Key: MAPREDUCE-279
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-279
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Components: jobtracker, tasktracker
> Reporter: Arun C Murthy
> Assignee: Arun C Murthy
> Fix For: 0.23.0
>
>
> Re-factor MapReduce into a generic resource scheduler and a per-job,
> user-defined component that manages the application execution.
--
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira
