[
https://issues.apache.org/jira/browse/HDFS-17915?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
ASF GitHub Bot updated HDFS-17915:
----------------------------------
Labels: pull-request-available (was: )
> Changes to the DN rack configuration on the NameNode do not take effect
> immediately.
> ------------------------------------------------------------------------------------
>
> Key: HDFS-17915
> URL: https://issues.apache.org/jira/browse/HDFS-17915
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Xiping Zhang
> Assignee: Xiping Zhang
> Priority: Major
> Labels: pull-request-available
>
> After adding a batch of DataNodes, we found that their rack information was
> incorrect and needed to be updated. However, the updated rack configuration
> did not take effect immediately after the DataNodes were restarted. Analysis
> showed that the NameNode was still caching the previous rack information, and
> the issue could only be resolved by restarting the NameNode.
> Restarting the NameNode is a costly operation, especially in very large
> clusters.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
