hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Tsz Wo (Nicholas), SZE (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HDFS-1200) The namenode could remember the last good location of a missing block
Date Fri, 11 Jun 2010 18:22:15 GMT

    [ https://issues.apache.org/jira/browse/HDFS-1200?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12877902#action_12877902
] 

Tsz Wo (Nicholas), SZE commented on HDFS-1200:
----------------------------------------------

It is a good idea if we can implement it with very little memory usage.

> The namenode could remember the last good location of a missing block
> ---------------------------------------------------------------------
>
>                 Key: HDFS-1200
>                 URL: https://issues.apache.org/jira/browse/HDFS-1200
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: name-node
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>
> There are times when datanodes die and all replicas of a block are lost. An fsck on the
HDFS reports these as "MISSING" blocks in the filesystem. The administrator has to go mine
through lots of namenode logs to find out which datanode(s) had a replica of that block. Then
the administrator can try to reboot that particular datanode to retrieve the missing block.
> This case can me made easier if the NN remembered the last known good replica location
of a block. An fsck command can report it and the it will help the administrator to determine
if that particular dead datanode can be brought back to life.

-- 
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