[
https://issues.apache.org/jira/browse/SPARK-18553?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Josh Rosen resolved SPARK-18553.
--------------------------------
Resolution: Fixed
Fix Version/s: 1.6.4
> Executor loss may cause TaskSetManager to be leaked
> ---------------------------------------------------
>
> Key: SPARK-18553
> URL: https://issues.apache.org/jira/browse/SPARK-18553
> Project: Spark
> Issue Type: Bug
> Components: Scheduler
> Affects Versions: 1.6.0, 2.0.0, 2.1.0
> Reporter: Josh Rosen
> Assignee: Josh Rosen
> Priority: Blocker
> Fix For: 1.6.4, 2.0.3, 2.1.0, 2.2.0
>
>
> Due to a bug in TaskSchedulerImpl, the complete sudden loss of an executor
> may cause a TaskSetManager to be leaked, causing ShuffleDependencies and
> other data structures to be kept alive indefinitely, leading to various types
> of resource leaks (including shuffle file leaks).
> In a nutshell, the problem is that TaskSchedulerImpl did not maintain its own
> mapping from executorId to running task ids, leaving it unable to clean up
> taskId to taskSetManager maps when an executor is totally lost.
--
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
