You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Benedict (JIRA)" <ji...@apache.org> on 2013/10/30 08:49:28 UTC

[jira] [Comment Edited] (CASSANDRA-5019) Still too much object allocation on reads

    [ https://issues.apache.org/jira/browse/CASSANDRA-5019?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13808819#comment-13808819 ] 

Benedict edited comment on CASSANDRA-5019 at 10/30/13 7:48 AM:
---------------------------------------------------------------

We could just allocate a new flyweight Column object when we want to read it. In most cases the reference is unlikely to escape, and they'll be allocated on stack.

Presumably in cases where they do escape we can either stop them from doing so or introduce some new method that converts them to a heavyweight Column. Not that this is likely to be a small task, having a look at it. Might be worth comparing performance with just this change and minimal optimisation work to see how it fairs, though?




was (Author: benedict):
Why not just allocate a new flyweight Column object when we want to read it? It's almost certainly going to be allocated on-stack.

> Still too much object allocation on reads
> -----------------------------------------
>
>                 Key: CASSANDRA-5019
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-5019
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Jonathan Ellis
>            Assignee: Yuki Morishita
>              Labels: performance
>             Fix For: 2.1
>
>
> ArrayBackedSortedColumns was a step in the right direction but it's still relatively heavyweight thanks to allocating individual Columns.



--
This message was sent by Atlassian JIRA
(v6.1#6144)