You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-issues@hadoop.apache.org by "Arpit Agarwal (JIRA)" <ji...@apache.org> on 2016/01/20 19:30:39 UTC

[jira] [Commented] (HDFS-9667) StorageType: SSD precede over DISK

    [ https://issues.apache.org/jira/browse/HDFS-9667?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15109073#comment-15109073 ] 

Arpit Agarwal commented on HDFS-9667:
-------------------------------------

Hi [~aderen], do you have an explanation for why the enum order matters? IIRC it should not.

Also as part of the 2.7.0 release we moved over StorageType to a different package. See HDFS-7806.

> StorageType: SSD precede over DISK
> ----------------------------------
>
>                 Key: HDFS-9667
>                 URL: https://issues.apache.org/jira/browse/HDFS-9667
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: namenode
>    Affects Versions: 2.6.0, 2.7.0
>            Reporter: ade
>            Assignee: ade
>             Fix For: 2.6.0
>
>         Attachments: HDFS-9667.0.patch
>
>
> We enabled the heterogeneous storage in our cluster and there are only ~50% of datanode & regionserver hosts with SSD. We set hfile with ONE_SSD storagepolicy but we found block's all replica are DISK often even local host with SSD storage. The block placement do not choose SSD first to place replica.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)