spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Mridul Muralidharan (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (SPARK-8297) Scheduler backend is not notified in case node fails in YARN
Date Thu, 11 Jun 2015 09:25:01 GMT

    [ https://issues.apache.org/jira/browse/SPARK-8297?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14581713#comment-14581713
] 

Mridul Muralidharan commented on SPARK-8297:
--------------------------------------------

kill -9 is not sufficient - sockets will get closed, which will cause akka to notify master.
To test, pulling the ethernet cable to the node should suffice.

Essentially, when the node goes completely MIA, spark-yarn does not handle it : example exceptions
while shuffle fetch would be something like NoRouteToHost, etc.

> Scheduler backend is not notified in case node fails in YARN
> ------------------------------------------------------------
>
>                 Key: SPARK-8297
>                 URL: https://issues.apache.org/jira/browse/SPARK-8297
>             Project: Spark
>          Issue Type: Bug
>          Components: YARN
>    Affects Versions: 1.2.2, 1.3.1, 1.4.1, 1.5.0
>         Environment: Spark on yarn - both client and cluster mode.
>            Reporter: Mridul Muralidharan
>            Priority: Critical
>
> When a node crashes, yarn detects the failure and notifies spark - but this information
is not propagated to scheduler backend (unlike in mesos mode, for example).
> It results in repeated re-execution of stages (due to FetchFailedException on shuffle
side), resulting finally in application failure.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

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


Mime
View raw message