[
https://issues.apache.org/jira/browse/CASSANDRA-15392?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17022051#comment-17022051
]
Jordan West commented on CASSANDRA-15392:
-----------------------------------------
{quote} As this relates to SASI, this wouldn’t be a regression right? I'd guess
we're already wasting TrivialOneToOne iterators?
{quote}
Correct. This wouldn't break SASI but it would waste TrivialOneToOne's most of
the time and rarely it would waste a ManyToOne that is oversized for its needs.
I haven't looked at FQL but for SASI I think its easy enough to just skip using
MergeIterators when they aren't needed / skip the pool when they are – happy to
submit a patch if its helpful.
> Pool Merge Iterators
> --------------------
>
> Key: CASSANDRA-15392
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15392
> Project: Cassandra
> Issue Type: Sub-task
> Components: Local/Compaction
> Reporter: Blake Eggleston
> Assignee: Blake Eggleston
> Priority: Normal
> Fix For: 4.0
>
>
> By pooling merge iterators, instead of creating new ones each time we need
> them, we can reduce garbage on the compaction and read paths under relevant
> workloads by ~4% in many cases.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
