[
https://issues.apache.org/jira/browse/MAPREDUCE-6608?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15143761#comment-15143761
]
Vinod Kumar Vavilapalli commented on MAPREDUCE-6608:
----------------------------------------------------
bq. I agree that storing state in zookeeper may have scalability issues. I am
just thinking that will it be ended up having too many small files in hdfs if
we are planning to store AM information in HDFS.
A solution for this is already given at YARN-1489 by [~bikassaha]. See this
comment:
https://issues.apache.org/jira/browse/YARN-1489?focusedCommentId=13862359&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-13862359.
The solution is essentially a combination of registry with YARN acting as a
distributed readers solution: Registry owns the write path and storage, RM/NMs
take care of providing scalable reads.
> Work Preserving AM Restart for MapReduce
> ----------------------------------------
>
> Key: MAPREDUCE-6608
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-6608
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Reporter: Srikanth Sampath
> Assignee: Srikanth Sampath
> Attachments: Patch1.patch, WorkPreservingMRAppMaster-1.pdf,
> WorkPreservingMRAppMaster-2.pdf, WorkPreservingMRAppMaster.pdf
>
>
> Providing a framework for work preserving AM is achieved in
> [YARN-1489|https://issues.apache.org/jira/browse/YARN-1489]. We would like
> to take advantage of this for MapReduce(MR) applications. There are some
> challenges which have been described in the attached document and few options
> discussed. We solicit feedback from the community.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
