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 09:17:35 UTC

[jira] [Created] (HDFS-10146) CLONE - Erasure Coding: Client no need to decode missing parity blocks

dragon created HDFS-10146:
-----------------------------

             Summary: CLONE - Erasure Coding: Client no need to decode missing parity blocks
                 Key: HDFS-10146
                 URL: https://issues.apache.org/jira/browse/HDFS-10146
             Project: Hadoop HDFS
          Issue Type: Sub-task
            Reporter: dragon
            Assignee: Walter Su
            Priority: Minor
             Fix For: HDFS-7285


Assume 6+3 schema.
Assume data block #2 is missing, then InputStream tries to read parity block #6.
Assume parity block #6 is missing too. And InputStream successfully reads parity block #7.
Then begin to decode.

Currently InputStream will decode #2 and #6. But client(user) only need #2. The parity block #6 will be disposed.

The improvement is we only decode #2.



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