You are viewing a plain text version of this content. The canonical link for it is here.

Posted to hdfs-dev@hadoop.apache.org by "dragon (JIRA)" <ji...@apache.org> on 2016/03/15 09:16:35 UTC

[jira] [Created] (HDFS-10055) CLONE - Erasure Coding: simplify the retry logic in DFSStripedInputStream (stateful read)

dragon created HDFS-10055:
-----------------------------

             Summary: CLONE - Erasure Coding: simplify the retry logic in DFSStripedInputStream (stateful read)
                 Key: HDFS-10055
                 URL: https://issues.apache.org/jira/browse/HDFS-10055
             Project: Hadoop HDFS
          Issue Type: Sub-task
            Reporter: dragon
            Assignee: Jing Zhao
             Fix For: HDFS-7285


Currently in DFSStripedInputStream the retry logic is still the same with DFSInputStream. More specifically, every failed read will try to search for another source node. And an exception is thrown when no new source node can be identified. This logic is not appropriate for EC inputstream and can be simplified.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)