[
https://issues.apache.org/jira/browse/HDFS-5027?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13719264#comment-13719264
]
Aaron T. Myers commented on HDFS-5027:
--------------------------------------
Why would you want to use fewer threads than the number of volumes configured?
What problem could occur by having an extra 10+ threads around only during DN
startup?
Having a handful of extra threads, particularly temporarily, is really not a
big deal. Note that the DN uses a separate thread for every transceiver during
it's normal operation, and the default value for the maximum number of these is
4096.
> On startup, DN should scan volumes in parallel
> ----------------------------------------------
>
> Key: HDFS-5027
> URL: https://issues.apache.org/jira/browse/HDFS-5027
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: datanode
> Affects Versions: 2.0.4-alpha
> Reporter: Aaron T. Myers
> Assignee: Aaron T. Myers
> Attachments: HDFS-5027.patch
>
>
> On startup the DN must scan all replicas on all configured volumes before the
> initial block report to the NN. This is currently done serially, but can be
> done in parallel to improve startup time of the DN.
--
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
