hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Steve Loughran (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-8928) Add ability to reset topologies on master nodes
Date Mon, 15 Oct 2012 09:52:04 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-8928?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13476058#comment-13476058

Steve Loughran commented on HADOOP-8928:

I do think this is good idea -we've discussed it before- I'm linking it up with HADOOP-8231;

* It should go into the HADOOP-7777 abstract switch mapping class with a recursive reset operation
that will stop at the first non-resettable topology mapping. 
* It also needs a remote way to reset the mappings, which is an extension of HADOOP-8232,
as a topology reset command would have to go into the {{dfsadmin}} and {{mradmin}} commands,
get sent to the manager node via an extended IPC, etc. 

> Add ability to reset topologies on master nodes
> -----------------------------------------------
>                 Key: HADOOP-8928
>                 URL: https://issues.apache.org/jira/browse/HADOOP-8928
>             Project: Hadoop Common
>          Issue Type: Improvement
>          Components: net
>            Reporter: Shinichi Yamashita
> For a topology decision of DataNode and TaskTracker, ScriptBasedMapping (probably TableMapping)
confirms HashMap first.
> To decide topology of DataNode and TaskTracker again, it is necessary to restart NameNode
and JobTracker.
> Therefore, it is necessary to change (or clear) HashMap function without restarting NameNode
and JobTracker.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

View raw message