hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Lohit Vijayarenu (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-3660) Add replication factor for injecting blocks in the data node cluster
Date Mon, 07 Jul 2008 20:44:32 GMT

     [ https://issues.apache.org/jira/browse/HADOOP-3660?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Lohit Vijayarenu updated HADOOP-3660:
-------------------------------------

    Attachment: dnc_inject.2.patch

+1 Looks good. I tested it and it replicates as places blocks as intended. One optimization
we could do is to obey the block placement policy when racks are specified, but we should
have it in a separate JIRA. I am re-attaching the patch against trunk which changed recently.


> Add replication factor for injecting blocks in the data node cluster 
> ---------------------------------------------------------------------
>
>                 Key: HADOOP-3660
>                 URL: https://issues.apache.org/jira/browse/HADOOP-3660
>             Project: Hadoop Core
>          Issue Type: Improvement
>    Affects Versions: 0.19.0
>            Reporter: Sanjay Radia
>            Assignee: Sanjay Radia
>             Fix For: 0.19.0
>
>         Attachments: dnc_inject.2.patch, dnc_inject.patch
>
>
> Data node cluster is used for testing and benchmarking.
> This jira improves it as follows:
>  - allows the user to specify the location of the data node dirs
>  - allows a replication factor to be specified for injected blocks.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message