[
https://issues.apache.org/jira/browse/HDDS-12929?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Siddhant Sangwan updated HDDS-12929:
------------------------------------
Summary: Datanode Should Immediately Trigger Container Close when Volume
Full (was: datanode trigger close container action immediately)
> Datanode Should Immediately Trigger Container Close when Volume Full
> --------------------------------------------------------------------
>
> Key: HDDS-12929
> URL: https://issues.apache.org/jira/browse/HDDS-12929
> Project: Apache Ozone
> Issue Type: Sub-task
> Components: Ozone Datanode
> Reporter: Sumit Agrawal
> Assignee: Siddhant Sangwan
> Priority: Minor
>
> SCM keeps allocating blocks till DN reports that the container is full. This
> is limitation as:
> * Blocks as written can be small like 1 KB to high as 256MB, so can not
> identify number of blocks at SCM
> * Communication from DN to SCM is every 30 seconds, and report handling at
> SCM may take time, so container size can not be guaranteed to be reported
> immediately.
>
> *An improvement is possible,*
> *ICR* for Container Close action, this can be reported more immediately.
>
> This will reduce the impact of write operation being rejected due to disk
> fail situation.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@ozone.apache.org
For additional commands, e-mail: issues-h...@ozone.apache.org
