[
https://issues.apache.org/jira/browse/CASSANDRA-9738?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14720557#comment-14720557
]
Ariel Weisberg commented on CASSANDRA-9738:
-------------------------------------------
I haven't looked to deep into it yet, but why would it be out for 3.0? Is it
not possible to bridge an off heap list with the on heap list implementation
that is already there?
The current formulation is out unless a benchmark of many rows per partition
demonstrates no slow down compared to the POJO version on a read intensive
benchmark with a cacheable distribution (not uniform).
If you can do it in time it's fine for 3.0.
> Migrate key-cache to be fully off-heap
> --------------------------------------
>
> Key: CASSANDRA-9738
> URL: https://issues.apache.org/jira/browse/CASSANDRA-9738
> Project: Cassandra
> Issue Type: Sub-task
> Reporter: Robert Stupp
> Assignee: Robert Stupp
> Fix For: 3.0 beta 2
>
>
> Key cache still uses a concurrent map on-heap. This could go to off-heap and
> feels doable now after CASSANDRA-8099.
> Evaluation should be done in advance based on a POC to prove that pure
> off-heap counter cache buys a performance and/or gc-pressure improvement.
> In theory, elimination of on-heap management of the map should buy us some
> benefit.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
