[
https://issues.apache.org/jira/browse/SPARK-33387?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Dongjoon Hyun updated SPARK-33387:
--
Description: Since the current shuffle block migration works in a random
order, the failure during worker decommission affects all of the shuffles. This
issue aims to support ordered migration. (was: Since the current shuffle block
migration works in a random order like the following, the failure during worker
decommission affects all of the shuffles. This issue aims to support ordered
migration.
shuffle_16_1900_0.index
shuffle_19_2123_0.index
shuffle_25_3792_0.index
shuffle_25_3792_0.data
shuffle_19_2123_0.data
shuffle_16_1900_0.data
shuffle_16_2015_0.index
shuffle_16_2015_0.data
shuffle_12_3264_0.index
shuffle_14_4329_0.index
shuffle_20_2463_0.index
shuffle_20_2463_0.data
shuffle_14_4329_0.data)
> Support ordered shuffle block migration
> ---
>
> Key: SPARK-33387
> URL: https://issues.apache.org/jira/browse/SPARK-33387
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
>Affects Versions: 3.1.0
>Reporter: Dongjoon Hyun
>Priority: Major
>
> Since the current shuffle block migration works in a random order, the
> failure during worker decommission affects all of the shuffles. This issue
> aims to support ordered migration.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
-
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org