hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Konstantin Shvachko (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HDFS-604) Block report processing for append
Date Tue, 08 Sep 2009 23:11:58 GMT

     [ https://issues.apache.org/jira/browse/HDFS-604?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Konstantin Shvachko updated HDFS-604:
-------------------------------------

    Attachment: BlockReportNN.patch

In the patch.
# The new {{reportDiff()}} forms four lists of blocks. Three of them did not change: the list
of replicas that should be added to the name-node, that should be removed from the name-node,
and blocks that the reporting data-node should invalidate.
The forth list is the list of corrupted replicas, which have either incorrect generation stamp
or a wrong length. This replicas are marked as corrupt, which triggers replication of the
remaining valid replicas, and will eventually invalidate the corrupt replica once the block
is fully replicated.
# {{addStoredBlock()}} completes a committed block once it reaches minimum replication.

> Block report processing for append
> ----------------------------------
>
>                 Key: HDFS-604
>                 URL: https://issues.apache.org/jira/browse/HDFS-604
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>          Components: name-node
>    Affects Versions: Append Branch
>            Reporter: Konstantin Shvachko
>            Assignee: Konstantin Shvachko
>             Fix For: Append Branch
>
>         Attachments: BlockReportNN.patch
>
>
> Implement new block report processing on the name-node as stated in the append design
and HDFS-576.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message