[
https://issues.apache.org/jira/browse/HDFS-4327?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13540223#comment-13540223
]
Suresh Srinivas commented on HDFS-4327:
---------------------------------------
Chris, please post a patch for this issue. I will commit it.
> Update documentation to more accurately describe Replication Pipelining
> -----------------------------------------------------------------------
>
> Key: HDFS-4327
> URL: https://issues.apache.org/jira/browse/HDFS-4327
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: datanode, documentation
> Affects Versions: 1.1.1, 2.0.2-alpha
> Reporter: Chris Embree
> Priority: Minor
> Labels: documentation
>
> A question was asked on the user list regarding data writes; do we write to
> disk then forward or do it async?
> According to Dev. "The received write packet is directly socket-written to
> the next node's receiver (async process - we don't wait for it to hit the disk
> there), and then written onto the disk of self()."
> Documentation here:
> http://hadoop.apache.org/docs/stable/hdfs_design.html#Replication+Pipelining
> is slightly outdated and ambiguous.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
