[
https://issues.apache.org/jira/browse/MAPREDUCE-279?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12999745#comment-12999745
]
Min Zhou commented on MAPREDUCE-279:
------------------------------------
@Arun
How does ApplicationMaster know its resource requirements before it launches
tasks? IMHO, the biggest problem of resources allocation is that we could't
determine the CPU/memory/disk/network requirements unless when the task is
running. User defined requirements by the configuration files are always
improper.
>From your words, the architecture allows end-users to implement any
>application-specific framework by implementing a custom ApplicationMaster.
>Even common users can deploy their ApplicationMaster over the cluster they
>have no any permissions on that? Can you illustrate how to achieve it?
> 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
