[
https://issues.apache.org/jira/browse/HDFS-6871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14103543#comment-14103543
]
Vinayakumar B commented on HDFS-6871:
-------------------------------------
[~umamaheswararao] and me discussed. This could create a problem of block miss
in-corner case of crash of Namenode before actual logSync and actual block
deletion by the datanode.
because, calling {{removeBlocks(collectedBlocks); // Incremental deletion of
blocks}} can make the heartbeat response to include deletion command for the
block.
So I feel, {{removeBlocks(..)}} call also should be extracted outside the lock.
and after the logSync.
> Improve NameNode performance when creating file
> -------------------------------------------------
>
> Key: HDFS-6871
> URL: https://issues.apache.org/jira/browse/HDFS-6871
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: namenode, performance
> Reporter: Yi Liu
> Assignee: Yi Liu
> Priority: Critical
> Fix For: 2.6.0
>
> Attachments: HDFS-6871.001.patch, HDFS-6871.002.patch
>
>
> Creating file with overwrite flag will cause NN fall into flush edit logs and
> block other requests if the file exists.
> When we create a file with overwrite flag (default is true) in HDFS, NN will
> remove original file if it exists. In FSNamesystem#startFileInternal, NN
> already holds the write lock, it calls {{deleteInt}} if the file exists,
> there is logSync in {{deleteInt}}. So in this case, logSync is under write
> lock, it will heavily affect the NN performance.
> We should ignore the force logSync in {{deleteInt}} in this case.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
