[
https://issues.apache.org/jira/browse/SPARK-30602?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17516298#comment-17516298
]
Min Shen commented on SPARK-30602:
----------------------------------
[~pan3793] , I guess you were referring to the earlier screenshot provided in
the JIRA.
The performance result in that screenshot is not representative of the final
results we see, since that was based on an earlier implementation which lacks
some of the key optimizations.
For the final results, you can refer to our [blog
post|[https://www.linkedin.com/pulse/bringing-next-gen-shuffle-architecture-data-linkedin-scale-min-shen/],]
which shows push based shuffle reduces both executor runtime and the end to
end runtime.
> SPIP: Support push-based shuffle to improve shuffle efficiency
> --------------------------------------------------------------
>
> Key: SPARK-30602
> URL: https://issues.apache.org/jira/browse/SPARK-30602
> Project: Spark
> Issue Type: Improvement
> Components: Shuffle, Spark Core
> Affects Versions: 3.1.0
> Reporter: Min Shen
> Assignee: Min Shen
> Priority: Major
> Labels: release-notes
> Fix For: 3.2.0
>
> Attachments: Screen Shot 2020-06-23 at 11.31.22 AM.jpg,
> vldb_magnet_final.pdf
>
>
> In a large deployment of a Spark compute infrastructure, Spark shuffle is
> becoming a potential scaling bottleneck and a source of inefficiency in the
> cluster. When doing Spark on YARN for a large-scale deployment, people
> usually enable Spark external shuffle service and store the intermediate
> shuffle files on HDD. Because the number of blocks generated for a particular
> shuffle grows quadratically compared to the size of shuffled data (# mappers
> and reducers grows linearly with the size of shuffled data, but # blocks is #
> mappers * # reducers), one general trend we have observed is that the more
> data a Spark application processes, the smaller the block size becomes. In a
> few production clusters we have seen, the average shuffle block size is only
> 10s of KBs. Because of the inefficiency of performing random reads on HDD for
> small amount of data, the overall efficiency of the Spark external shuffle
> services serving the shuffle blocks degrades as we see an increasing # of
> Spark applications processing an increasing amount of data. In addition,
> because Spark external shuffle service is a shared service in a multi-tenancy
> cluster, the inefficiency with one Spark application could propagate to other
> applications as well.
> In this ticket, we propose a solution to improve Spark shuffle efficiency in
> above mentioned environments with push-based shuffle. With push-based
> shuffle, shuffle is performed at the end of mappers and blocks get pre-merged
> and move towards reducers. In our prototype implementation, we have seen
> significant efficiency improvements when performing large shuffles. We take a
> Spark-native approach to achieve this, i.e., extending Spark’s existing
> shuffle netty protocol, and the behaviors of Spark mappers, reducers and
> drivers. This way, we can bring the benefits of more efficient shuffle in
> Spark without incurring the dependency or overhead of either specialized
> storage layer or external infrastructure pieces.
>
> Link to dev mailing list discussion:
> [http://apache-spark-developers-list.1001551.n3.nabble.com/Enabling-push-based-shuffle-in-Spark-td28732.html]
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
