[
https://issues.apache.org/jira/browse/CASSANDRA-15393?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16964202#comment-16964202
]
Blake Eggleston commented on CASSANDRA-15393:
---------------------------------------------
I had not, this group of changes was developed on 3.0 then ported up to trunk.
That would neatly fix the concerns with this ticket and CASSANDRA-15391 though.
Something that's not immediately clear to me (and I'm not really familiar with
off heap memtables at all), is how we'd prevent the amount of memory used off
heap from growing too large. Reclaiming after the parent partition has been
closed would be too long to wait in the case of huge partitions, and the
lifecycle of Unfiltered instances rely on the garbage collector cleaning things
up. Any thoughts there?
> Add byte array backed cells
> ---------------------------
>
> Key: CASSANDRA-15393
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15393
> Project: Cassandra
> Issue Type: Sub-task
> Components: Local/Compaction
> Reporter: Blake Eggleston
> Assignee: Blake Eggleston
> Priority: Normal
> Fix For: 4.0
>
>
> We currently materialize all values as on heap byte buffers. Byte buffers
> have a fairly high overhead given how frequently they’re used, and on the
> compaction and local read path we don’t do anything that needs them. Use of
> byte buffer methods only happens on the coordinator. Using cells that are
> backed by byte arrays instead in these situations reduces compaction and read
> garbage up to 22% in many cases.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
