You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (Jira)" <ji...@apache.org> on 2022/10/28 13:33:00 UTC
[jira] [Commented] (SPARK-40950) isRemoteAddressMaxedOut performance overhead on scala 2.13
[ https://issues.apache.org/jira/browse/SPARK-40950?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17625710#comment-17625710 ]
Apache Spark commented on SPARK-40950:
--------------------------------------
User 'eejbyfeldt' has created a pull request for this issue:
https://github.com/apache/spark/pull/38427
> isRemoteAddressMaxedOut performance overhead on scala 2.13
> ----------------------------------------------------------
>
> Key: SPARK-40950
> URL: https://issues.apache.org/jira/browse/SPARK-40950
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Affects Versions: 3.2.2, 3.3.1
> Reporter: Emil Ejbyfeldt
> Priority: Major
>
> On scala 2.13 the blocks in FetchRequest is sometimes backed by a `List` while in 2.12 it would be ArrayBuffer. This means that calculating the length of the blocks which is done in isRemoteAddressMaxedOut and other places now much more expensive. This is because in 2.13 `Seq` is can no longer be backed by a mutable collection.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org