[
https://issues.apache.org/jira/browse/HDFS-15419?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17139292#comment-17139292
]
Ayush Saxena commented on HDFS-15419:
-------------------------------------
I think this has been somewhere discussed before as well.
Router is just a proxy, It just needs to take the call from the client and
proxy to the nameservice, and whatever response it gets from the nameservice it
has to give it back to the actual client.
It is up to the actual client discretion whether it want's to wait/retry or
not. Holding and retrying a call at Router doesn't seems much apt to me.
The retry logics are already there at the Client side codes, This may lead to
double retries too, and would be better the client only decides whether he
needs to try again or not.
> Router should retry communicate with NN when cluster is unavailable using
> configurable time interval
> ----------------------------------------------------------------------------------------------------
>
> Key: HDFS-15419
> URL: https://issues.apache.org/jira/browse/HDFS-15419
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: configuration, hdfs-client, rbf
> Reporter: bhji123
> Priority: Major
>
> When cluster is unavailable, router -> namenode communication will only retry
> once without any time interval, that is not reasonable.
> For example, in my company, which has several hdfs clusters with more than
> 1000 nodes, we have encountered this problem. In some cases, the cluster
> becomes unavailable briefly for about 10 or 30 seconds, at the same time,
> almost all rpc requests to router failed because router only retry once
> without time interval.
> It's better for us to enhance the router retry strategy, to retry
> **communicate with NN using configurable time interval and max retry times.
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
