[
https://issues.apache.org/jira/browse/CASSANDRA-9988?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16097112#comment-16097112
]
Jay Zhuang commented on CASSANDRA-9988:
---------------------------------------
I added tests for different cell size and 10K and 100K b-tree size:
| branch | utest |
|[9988-trunk|https://github.com/cooldoger/cassandra/tree/9988-trunk]|[circleci#41|https://circleci.com/gh/cooldoger/cassandra/41]|
|[9988-nofix|https://github.com/cooldoger/cassandra/tree/9988-nofix]||
If the data could fit into one leaf node (<=32), the performance is
significantly improved. Otherwise, there's no performance difference,
regardless of the cell size.
!9988-data.png|data!
!9988-result.png|result!
> Introduce leaf-only iterator
> ----------------------------
>
> Key: CASSANDRA-9988
> URL: https://issues.apache.org/jira/browse/CASSANDRA-9988
> Project: Cassandra
> Issue Type: Sub-task
> Reporter: Benedict
> Assignee: Jay Zhuang
> Priority: Minor
> Labels: patch
> Fix For: 4.0
>
> Attachments: 9988-data.png, 9988-result.png, 9988-trunk-new.txt,
> 9988-trunk-new-update.txt, trunk-9988.txt
>
>
> In many cases we have small btrees, small enough to fit in a single leaf
> page. In this case it _may_ be more efficient to specialise our iterator.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
