[
https://issues.apache.org/jira/browse/YARN-1029?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13855800#comment-13855800
]
Karthik Kambatla commented on YARN-1029:
----------------------------------------
bq. There is a separate jira open to add a cluster-id
Here, we use cluster-id to make sure the RM to which the bread-crumb
corresponds to is in the same cluster. In HDFS, they directly check for the
other NN's id, which restricts us to a single standby. For RM HA, there is no
reason to limit ourselves to two RMs, even though that is probably going to be
default deployment. The actual token-related logic can be handled in the other
JIRA.
bq. this is probably not enough. we need to notify the rm.
Just to be sure, are you suggesting we add a new event and a handler in the RM
for that event?
I have addressed other comments, and looking at the test failure from the
previous patch. Will incorporate any other comments and post a patch at the
earliest.
> Allow embedding leader election into the RM
> -------------------------------------------
>
> Key: YARN-1029
> URL: https://issues.apache.org/jira/browse/YARN-1029
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Bikas Saha
> Assignee: Karthik Kambatla
> Attachments: embedded-zkfc-approach.patch, yarn-1029-0.patch,
> yarn-1029-0.patch, yarn-1029-1.patch, yarn-1029-approach.patch
>
>
> It should be possible to embed common ActiveStandyElector into the RM such
> that ZooKeeper based leader election and notification is in-built. In
> conjunction with a ZK state store, this configuration will be a simple
> deployment option.
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)
