[
https://issues.apache.org/jira/browse/HDDS-15463?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18146014#comment-18146014
]
Rui Wang commented on HDDS-15463:
---------------------------------
[~sodonnell] nothing comes without a price. I am trying to reason the cost of
the short lives pipeline, and it seems to me that it needs: "adjusting for the
constantly changing space usage on the cluster.". I am afraid this is not easy
neither and would carry its own complexity.
The philosophy of this new propose is to apply incremental change: we maintain
it much similar to Ratis pipeline but kill the known complexity, such as
QUASI_CLOSE state for containers so this proposal has its value proposition.
Existing Ratis pipelines have issues but they have served the real use cases.
We just choose to be conservative to incrementally improve things.
Meanwhile, it is not guaranteed that short lived pipeline will work perfect
fine from day 0 and it needs time to become mature. IMO the proposal in this
Jira and the short-lived pipeline do not contradict each other; rather, they
seem to be orthogonal and tackle the known issues at different levels.
> Streaming Write Pipeline without Raft
> -------------------------------------
>
> Key: HDDS-15463
> URL: https://issues.apache.org/jira/browse/HDDS-15463
> Project: Apache Ozone
> Issue Type: New Feature
> Components: Ozone Client, Ozone Datanode
> Reporter: Tsz-wo Sze
> Assignee: Tsz-wo Sze
> Priority: Major
> Labels: pull-request-available
> Attachments: 20260712HDDS-15463 Streaming Write Pipeline without
> Raft.pdf
>
>
> - V1) Raft Pipeline: Use Raft for both WriteChunk and PutBlock
> - V2)Streaming Write Pipeline (HDDS-4454): Use Ratis streaming (RATIS-979)
> for WriteChunk and Raft for PutBlock
> - V3) Streaming Write Pipeline without Raft: Use Ratis streaming for both
> WriteChunk and PutBlock.
> We implement V3 in this JIRA. Will post a design and create subtasks.
--
This message was sent by Atlassian Jira
(v10.3.26#10030026)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]