[
https://issues.apache.org/jira/browse/HADOOP-990?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Raghu Angadi updated HADOOP-990:
--------------------------------
Status: Open (was: Patch Available)
> This is not required. Datanode already considers only 98% of total disk space
> (dfs.datanode.du.pct).
dfs.datanode.du.pct does not work as expected. Freespace is calculated as
'0.98*disk_free_space'. I think it should be 'MAX(0.98*total_disk_space -
disk_used, 0)', right?. I will add this to patch.
> Datanode doesn't retry when write to one (full)drive fail
> ---------------------------------------------------------
>
> Key: HADOOP-990
> URL: https://issues.apache.org/jira/browse/HADOOP-990
> Project: Hadoop
> Issue Type: Bug
> Components: dfs
> Reporter: Koji Noguchi
> Assigned To: Raghu Angadi
> Attachments: HADOOP-990-1.patch, HADOOP-990-2.patch
>
>
> When one drive is 99.9% full and datanode choose that drive to write, it
> fails with
> 2007-02-07 18:16:56,574 WARN org.apache.hadoop.dfs.DataNode: DataXCeiver
> org.apache.hadoop.util.DiskChecker$DiskOutOfSpaceException: No space left on
> device
> at org.apache.hadoop.dfs.DataNode$DataXceiver.writeBlock(DataNode.java:801)
> at org.apache.hadoop.dfs.DataNode$DataXceiver.run(DataNode.java:563)
> at java.lang.Thread.run(Thread.java:595)
> Combined with HADOOP-940, these failed blocks stay under-replicated.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
