[
https://issues.apache.org/jira/browse/HDFS-6452?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14010598#comment-14010598
]
Aaron T. Myers commented on HDFS-6452:
--------------------------------------
Hi Gera, while this will obviously halve the amount of errant RPCs made to a
standby NN in the situation where all clients connect to the standby NN first,
it will of course also cut in half the number of RPCs that connect to the
active the first time in the situation where all clients connect to the active
first. Given that, is this proposal really a net improvement?
> ConfiguredFailoverProxyProvider should randomize currentProxyIndex on
> initialization
> ------------------------------------------------------------------------------------
>
> Key: HDFS-6452
> URL: https://issues.apache.org/jira/browse/HDFS-6452
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: ha, hdfs-client
> Affects Versions: 2.4.0
> Reporter: Gera Shegalov
> Assignee: Gera Shegalov
>
> We observe that the clients iterate proxies in the fixed order. Depending on
> the order of namenodes in dfs.ha.namenodes.<nameservice> (e.g. 'nn1,nn2') and
> the current standby (nn1), all the clients will hit nn1 first, and then
> failover to nn2. Chatting with [~lohit] we think we can simply select the
> initial value of {{currentProxyIndex}} randomly, and keep the logic of
> {{performFailover}} of iterating from left-to-right. This should halve the
> unnecessary load on standby NN.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
