[
https://issues.apache.org/jira/browse/HDDS-1452?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16823378#comment-16823378
]
Anu Engineer commented on HDDS-1452:
------------------------------------
{quote}If a container is full of 1KB files it may not be a good candidate for
Erasure Coding. If your entire
{quote}
In the ozone world, it should not matter. Especially since we plan to EC at the
level of data or containers. The actual EC would not work on RockDB, but it
should work on all containers, irrespective of the data size of the actual keys.
{quote}cluster is full of 1KB files then we have other serious problems, of
course.
{quote}
Hopefully, Ozone will be just be able to handle this scenario, we might need
many Ozone Managers, but a single SCM and few data nodes. I am not advising
this model, but it is something that I am sure we will run into eventually,
especially since we are an object store; the HDFS use case is different; but in
the ozone world I think we will have to be prepared for this eventuality.
> All chunks should happen to a single file for a block in datanode
> -----------------------------------------------------------------
>
> Key: HDDS-1452
> URL: https://issues.apache.org/jira/browse/HDDS-1452
> Project: Hadoop Distributed Data Store
> Issue Type: Bug
> Components: Ozone Datanode
> Affects Versions: 0.5.0
> Reporter: Shashikant Banerjee
> Assignee: Shashikant Banerjee
> Priority: Major
> Fix For: 0.5.0
>
>
> Currently, all chunks of a block happen to individual chunk files in
> datanode. This idea here is to write all individual chunks to a single file
> in datanode.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
