You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "He Qi (Jira)" <ji...@apache.org> on 2023/03/08 12:48:00 UTC
[jira] [Updated] (SPARK-42719) `MapOutputTracker#getPreferredLocations` should respect `spark.shuffle.reduceLocality.enabled`
[ https://issues.apache.org/jira/browse/SPARK-42719?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
He Qi updated SPARK-42719:
--------------------------
Summary: `MapOutputTracker#getPreferredLocations` should respect `spark.shuffle.reduceLocality.enabled` (was: `Map#getPreferredLocations` should respect `spark.shuffle.reduceLocality.enabled`)
> `MapOutputTracker#getPreferredLocations` should respect `spark.shuffle.reduceLocality.enabled`
> -----------------------------------------------------------------------------------------------
>
> Key: SPARK-42719
> URL: https://issues.apache.org/jira/browse/SPARK-42719
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Affects Versions: 3.5.0
> Reporter: He Qi
> Priority: Major
>
> Discuss as [https://github.com/apache/spark/pull/40307]
> {{getPreferredLocations}} in {{ShuffledRowRDD}} should return {{Nil}} at the very beginning in case {{spark.shuffle.reduceLocality.enabled = false}} (conceptually).
> This logic is pushed into MapOutputTracker though - and {{getPreferredLocationsForShuffle}} honors {{spark.shuffle.reduceLocality.enabled}} - but {{getMapLocation}} does not.
> So the fix would be to fix {{getMapLocation}} to honor the parameter.
--
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