[
https://issues.apache.org/jira/browse/HDFS-1108?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13089683#comment-13089683
]
Todd Lipcon commented on HDFS-1108:
-----------------------------------
bq. This should be similar to how we treat setTime(). Please don't add logSync
on every addBlock().
The difference is that, if we miss a setTime() call, the worst thing that
happens is that on failover, one of the files has an out-of-date access time.
This is not a dataloss.
If we miss a persistBlocks(), on failover we will lose data. This is dataloss,
and unacceptable.
How do you propose to avoid this dataloss? Or are you suggesting that dataloss
on failover is acceptable?
> Log newly allocated blocks
> --------------------------
>
> Key: HDFS-1108
> URL: https://issues.apache.org/jira/browse/HDFS-1108
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: name-node
> Reporter: dhruba borthakur
> Assignee: Todd Lipcon
> Fix For: HA branch (HDFS-1623)
>
> Attachments: HDFS-1108.patch, hdfs-1108-habranch.txt, hdfs-1108.txt
>
>
> The current HDFS design says that newly allocated blocks for a file are not
> persisted in the NN transaction log when the block is allocated. Instead, a
> hflush() or a close() on the file persists the blocks into the transaction
> log. It would be nice if we can immediately persist newly allocated blocks
> (as soon as they are allocated) for specific files.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
