[
https://issues.apache.org/jira/browse/RATIS-979?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17286966#comment-17286966
]
Tsz-wo Sze commented on RATIS-979:
----------------------------------
The length in OzoneManager is updated at the end but not during write.
Also, Ozone is different from HDFS since the replication unit is container.
When there are multiple clients writing to the same container concurrently, we
need to make sure the container is consistent. If the consistency is provided
by OzoneManager, each writeChunk need to update the metadata in OzoneManager.
In that case, an OzoneManager acts like a Namenode.
> Ratis streaming
> ---------------
>
> Key: RATIS-979
> URL: https://issues.apache.org/jira/browse/RATIS-979
> Project: Ratis
> Issue Type: New Feature
> Components: Streaming
> Reporter: Tsz-wo Sze
> Assignee: Tsz-wo Sze
> Priority: Major
> Attachments: RatisStreaming20200929.pdf, screenshot-1.png,
> screenshot-2.png, screenshot-3.png
>
>
> In this JIRA, we design and implement Ratis Streaming with zero buffer
> copying and asynchronous event driven.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
