hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Fengdong Yu (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-5027) On startup, DN should scan volumes in parallel
Date Thu, 25 Jul 2013 05:13:48 GMT

    [ https://issues.apache.org/jira/browse/HDFS-5027?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13719236#comment-13719236
] 

Fengdong Yu commented on HDFS-5027:
-----------------------------------

Aaron,
{code}
+    for (final FsVolumeImpl v : volumes) {
+      Thread t = new Thread() {
{code}

so, is it possible that you create a large numbers of threads? can you use ExecutorService
and make threads number configurable?


                
> 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

Mime
View raw message