[
https://issues.apache.org/jira/browse/HDFS-13522?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17557699#comment-17557699
]
Owen O'Malley commented on HDFS-13522:
--------------------------------------
I'm concerned about additional msyncs on every call from RBF. It will radically
increase the rpc load on the active NN.
I'd propose that we add a new field in the client protocol that tracks the
state of all of the namespaces that a given client has used. The flow would
look like:
client -> router: {} // no state
router -> nn: msync // get the state
nn -> router: state 1000
router -> client: \{ns1: 1000}
client -> router: \{ns1: 1000}
router -> observer: state 1000
The client just gives back the state it was given. This gracefully handles fail
overs between routers and avoids additional msyncs.
> RBF: Support observer node from Router-Based Federation
> -------------------------------------------------------
>
> Key: HDFS-13522
> URL: https://issues.apache.org/jira/browse/HDFS-13522
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: federation, namenode
> Reporter: Erik Krogen
> Assignee: Simbarashe Dzinamarira
> Priority: Major
> Labels: pull-request-available
> Attachments: HDFS-13522.001.patch, HDFS-13522.002.patch,
> HDFS-13522_WIP.patch, RBF_ Observer support.pdf, Router+Observer RPC
> clogging.png, ShortTerm-Routers+Observer.png
>
> Time Spent: 15h 20m
> Remaining Estimate: 0h
>
> Changes will need to occur to the router to support the new observer node.
> One such change will be to make the router understand the observer state,
> e.g. {{FederationNamenodeServiceState}}.
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
