[
https://issues.apache.org/jira/browse/HDFS-12778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Virajith Jalaparti updated HDFS-12778:
--------------------------------------
Attachment: HDFS-12778-HDFS-9806.001.patch
Attaching a patch where {{getBlockLocations}} on a PROVIDED file will return
the default number of replicas configured ({{dfs.replication}}). More
precisely, the number of locations returned for PROVIDED files = (number of
local replicas) + min({{dfs.replication}} - (number of local replicas), number
of datanodes configured with PROVIDED storage type).
The patch also fixes the affected unit tests in
{{TestNameNodeProvidedImplementation}}.
> [READ] Report multiple locations for PROVIDED blocks
> ----------------------------------------------------
>
> Key: HDFS-12778
> URL: https://issues.apache.org/jira/browse/HDFS-12778
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Virajith Jalaparti
> Assignee: Virajith Jalaparti
> Attachments: HDFS-12778-HDFS-9806.001.patch
>
>
> On {{getBlockLocations}}, only one Datanode is returned as the location for
> all PROVIDED blocks. This can hurt the performance of applications which
> typically 3 locations per block. We need to return multiple Datanodes for
> each PROVIDED block for better application performance/resilience.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
