[
https://issues.apache.org/jira/browse/HDFS-9917?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15196635#comment-15196635
]
Brahma Reddy Battula commented on HDFS-9917:
--------------------------------------------
bq. I suggest that NN could just ignore the pending IBRs before the first full
BR. Would it fix the problem?
Yes, I think its same as clearing on reRegister() at datanode itself.
Advantage of clearing on reRegister() in DN itself, is
unnecessary RPC will go to namenode and Namenode need to unnecessary GC for
these IBR's..
We may also need to limit the DN keep accumulating the IBRs and use lot of
memory
> IBR accumulate more objects when SNN was down for sometime.
> -----------------------------------------------------------
>
> Key: HDFS-9917
> URL: https://issues.apache.org/jira/browse/HDFS-9917
> Project: Hadoop HDFS
> Issue Type: Bug
> Reporter: Brahma Reddy Battula
> Assignee: Brahma Reddy Battula
>
> SNN was down for sometime because of some reasons..After restarting SNN,it
> became unreponsive because
> - 29 DN's sending IBR in each 5 million ( most of them are delete IBRs),
> where as each datanode had only ~2.5 million blocks.
> - GC can't trigger on this objects since all will be under RPC queue.
> To recover this( to clear this objects) ,restarted all the DN's one by
> one..This issue happened in 2.4.1 where split of blockreport was not
> available.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
