[
https://issues.apache.org/jira/browse/HDFS-15255?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17077254#comment-17077254
]
Lisheng Sun commented on HDFS-15255:
------------------------------------
Thanx [~sodonnell] for your Test.
According to your result, in current code Collections.shuffle(list) is invalid
if readConsiderLoad is set. This changed the intention. If there are two
nodes with same distance and load, it will not shuffle and choose only one node.
I think it is a bug and take it out from createSecondaryNodeSorter.
And what do you have good suggetion for findbugs warning? Thank you.
> Consider StorageType when DatanodeManager#sortLocatedBlock()
> ------------------------------------------------------------
>
> Key: HDFS-15255
> URL: https://issues.apache.org/jira/browse/HDFS-15255
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Lisheng Sun
> Assignee: Lisheng Sun
> Priority: Major
> Attachments: HDFS-15255.001.patch, HDFS-15255.002.patch
>
>
> When only one replica of a block is SDD, the others are HDD.
> When the client reads the data, the current logic is that it considers the
> distance between the client and the dn. I think it should also consider the
> StorageType of the replica. Priority to return a replica of the specified
> StorageType
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
