[
https://issues.apache.org/jira/browse/HDFS-9103?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14901213#comment-14901213
]
James Clampffer commented on HDFS-9103:
---------------------------------------
I agree with Bob that the C++ API should be reasonably usable on its own; it
might not be tuned perfectly but that could be added incrementally on the user
side. We could supply callback(s) to handle different sorts of failures later,
something like InputStream::onDroppedConnection. The InputStream will still
handle the failure it but it allows a user to see what's going on.
Just to be safe it might be worth wrapping previously_excluded_datanodes in a
lock. Or we should agree on threading semantics that say it doesn't need one
there.
Otherwise +1
> Retry reads on DN failure
> -------------------------
>
> Key: HDFS-9103
> URL: https://issues.apache.org/jira/browse/HDFS-9103
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: hdfs-client
> Reporter: Bob Hansen
> Assignee: Bob Hansen
> Fix For: HDFS-8707
>
> Attachments: HDFS-9103.1.patch, HDFS-9103.2.patch
>
>
> When AsyncPreadSome fails, add the failed DataNode to the excluded list and
> try again.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
