[jira] [Commented] (HDFS-6469) Coordinated replication of the namespace using ConsensusNode

["Suresh Srinivas (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HDFS-6469?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14020375#comment-14020375 ] 

Suresh Srinivas commented on HDFS-6469:
---------------------------------------

I had a cursory look at the document. I am very uncomfortable about adding all this complexity into HDFS. What do others think?

Some very high level comments:
- It would be good to understand the clear advantages and disadvantages (slowdown due to consensus) of this solution.
- Would be great to know failure handling. For example what happens when a change cannot be journaled after consensus is reached and memory is updated.
- How are requests from other clients handled when a request is being processed? If they are blocked, is this not making what is sighted as bottleneck currently, the namenode single lock, much worser?

I plan on catching up on this proposal completely and respond back early next week.

A related question. Given your focus on this, are you going to abandon BackupNode based solutions?

> Coordinated replication of the namespace using ConsensusNode
> ------------------------------------------------------------
>
>                 Key: HDFS-6469
>                 URL: https://issues.apache.org/jira/browse/HDFS-6469
>             Project: Hadoop HDFS
>          Issue Type: New Feature
>          Components: namenode
>    Affects Versions: 3.0.0
>            Reporter: Konstantin Shvachko
>            Assignee: Konstantin Shvachko
>         Attachments: CNodeDesign.pdf
>
>
> This is a proposal to introduce ConsensusNode - an evolution of the NameNode, which enables replication of the namespace on multiple nodes of an HDFS cluster by means of a Coordination Engine.



--
This message was sent by Atlassian JIRA
(v6.2#6252)