[
https://issues.apache.org/jira/browse/HDFS-13488?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16446511#comment-16446511
]
Íñigo Goiri commented on HDFS-13488:
------------------------------------
After adding the unit test for the client failover across Routers, I realized
that the exception has to be {{StandbyException}} for it to work.
It cannot just be a subclass as the retry policy uses
{{RemoteException#unwrapRemoteException(StandbyException.class)}}.
For this reason I removed the {{RouterSafeModeException}}.
Other than that, [^HDFS-13488.000.patch] should be able to the resiliency to
overloaded subclusters.
To handle these scenarios, one can also use HDFS-13484.
> RBF: Reject requests when a Router is overloaded
> ------------------------------------------------
>
> Key: HDFS-13488
> URL: https://issues.apache.org/jira/browse/HDFS-13488
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Íñigo Goiri
> Assignee: Íñigo Goiri
> Priority: Major
> Attachments: HDFS-13488.000.patch
>
>
> A Router might be overloaded when handling special cases (e.g. a slow
> subcluster). The Router could reject the requests and the client could try
> with another Router. We should leverage the Standby mechanism for this.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
