[
https://issues.apache.org/jira/browse/SPARK-18607?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15701683#comment-15701683
]
Apache Spark commented on SPARK-18607:
--------------------------------------
User 'Ru-Xiang' has created a pull request for this issue:
https://github.com/apache/spark/pull/16033
> give a result on a percent of the tasks succeed
> ------------------------------------------------
>
> Key: SPARK-18607
> URL: https://issues.apache.org/jira/browse/SPARK-18607
> Project: Spark
> Issue Type: New Feature
> Components: Spark Core
> Reporter: Ru Xiang
> Labels: patch
>
> In this patch, we modify the codes corresponding to runApproximateJob so that
> we can get a result when the specified percent of tasks succeed.
> In a production environment, 'long tail' is a common urgent problem. In
> practice, as long as we can get a specified percent of tasks' results, we
> can guarantee the final results. And this is a common requirement in the
> practice of machine learning algorithms.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
