[
https://issues.apache.org/jira/browse/HDFS-4053?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13478407#comment-13478407
]
Harsh J commented on HDFS-4053:
-------------------------------
bq. I'm sure we have a conversion method lurking somewhere in hadoop.
This is already available. You can set dfs.blocksize as "128m" on trunk and it
will be read fine.
> Increase the default block size
> -------------------------------
>
> Key: HDFS-4053
> URL: https://issues.apache.org/jira/browse/HDFS-4053
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Eli Collins
> Assignee: Eli Collins
> Attachments: hdfs-4053.txt, hdfs-4053.txt, hdfs-4053.txt
>
>
> The default HDFS block size ({{dfs.blocksize}}) has been 64mb forever. 128mb
> works well in practice on today's hardware configurations, most clusters I
> work with use it or higher (eg 256mb). Let's bump to 128mb in trunk for v3.
--
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
