You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@lucene.apache.org by "Atri Sharma (Jira)" <ji...@apache.org> on 2020/07/16 10:43:00 UTC
[jira] [Commented] (LUCENE-9432) Use LinkedList instead of manual
array re-sizing for better throughput.
[ https://issues.apache.org/jira/browse/LUCENE-9432?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17159106#comment-17159106 ]
Atri Sharma commented on LUCENE-9432:
-------------------------------------
Can you share some benchmarks of the changes you saw?
Arrays have a smaller memory footprint compared to linked lists and are more cacheable in CPU caches than linked lists. I would not expect a massive performance difference due to the array resizing – but it will be good to see numbers.
> Use LinkedList instead of manual array re-sizing for better throughput.
> -----------------------------------------------------------------------
>
> Key: LUCENE-9432
> URL: https://issues.apache.org/jira/browse/LUCENE-9432
> Project: Lucene - Core
> Issue Type: Improvement
> Components: core/codecs
> Reporter: Mohammad Sadiq
> Priority: Minor
> Labels: patch-available, performance, pull-request-available
> Attachments: LUCENE-9432.patch
>
>
> I observed that using {{LinkedList}} instead of manually re-sizing and copying {{SegmentTermEnumFrame}}s improves red-line QPS. Does it make sense to include this?
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org