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 2018/02/01 16:51:00 UTC

[jira] [Commented] (SPARK-8835) Provide pluggable Congestion Strategies to deal with Streaming load

    [ https://issues.apache.org/jira/browse/SPARK-8835?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16348886#comment-16348886 ] 

Apache Spark commented on SPARK-8835:
-------------------------------------

User 'EmergentOrder' has created a pull request for this issue:
https://github.com/apache/spark/pull/20478

> Provide pluggable Congestion Strategies to deal with Streaming load
> -------------------------------------------------------------------
>
>                 Key: SPARK-8835
>                 URL: https://issues.apache.org/jira/browse/SPARK-8835
>             Project: Spark
>          Issue Type: Sub-task
>          Components: DStreams
>            Reporter: François Garillot
>            Priority: Major
>
> Second part of [SPARK-7398|https://issues.apache.org/jira/browse/SPARK-7398] (which has an over-arching, high-level design doc).
> An (outdated) [PoC implementation|https://github.com/huitseeker/spark/tree/ReactiveStreamingBackPressureControl/] exists.
> Note that throttling in the current (Spark 1.5.0) way pushes down the (fast-overflowing) buffer of received elements down to the TCP stack, which then has to deal with the break. This can be witnessed here :
> https://github.com/skyluc/spark-streaming-testbed/tree/test-runs-006/test-runs-006



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org