[
https://issues.apache.org/jira/browse/HDFS-13522?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17692377#comment-17692377
]
Simbarashe Dzinamarira commented on HDFS-13522:
-----------------------------------------------
Hi [~tasanuma]
I agree porting back these changes to 2.7.x would be more work.
Regarding Design A and Design B. Initially, Design A would msync only for the
first call, while Design B would always msync. The decision to msync or not
would just be governed by whether the federatedState is present in the RPC
header.
We then changed Design A to direct the first call to the active instead of
msync. With this change, it is then more complicated to add the always msync
option since more information is needed to distinguish between 1) a new client
performing its first call. 2) An old client performing an n-th call. So right
now we do not have design B implemented.
One part of design B that is implemented is limiting the rpc size, through
"dfs.federation.router.observer.federated.state.propagation.maxsize". However,
instead of falling back to always-msync, it falls back to directing calls to
the active.
There is no active discussion of adding in the always-msync behavior.
> HDFS-13522: Add federated nameservices states to client protocol and
> propagate it between routers and clients.
> --------------------------------------------------------------------------------------------------------------
>
> 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
> Fix For: 3.4.0
>
> 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,
> observer_reads_in_rbf_proposal_simbadzina_v1.pdf,
> observer_reads_in_rbf_proposal_simbadzina_v2.pdf
>
> Time Spent: 20h 50m
> 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 patch captures the state of all namespaces in the routers and propagates
> it to clients. A follow up patch will change router behavior to direct
> requests to the observer.
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
