spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Andrew Or (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (SPARK-12583) spark shuffle fails with mesos after 2mins
Date Mon, 22 Feb 2016 19:22:18 GMT

     [ https://issues.apache.org/jira/browse/SPARK-12583?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Andrew Or updated SPARK-12583:
------------------------------
    Target Version/s: 2.0.0  (was: 1.6.1)

> spark shuffle fails with mesos after 2mins
> ------------------------------------------
>
>                 Key: SPARK-12583
>                 URL: https://issues.apache.org/jira/browse/SPARK-12583
>             Project: Spark
>          Issue Type: Bug
>          Components: Shuffle
>    Affects Versions: 1.6.0
>            Reporter: Adrian Bridgett
>
> See user mailing list "Executor deregistered after 2mins" for more details.
> As of 1.6, the driver registers with each shuffle manager via  MesosExternalShuffleClient.
 Once this disconnects, the shuffle manager automatically cleans up the data associate with
that driver.
> However, the connection is terminated before this happens as it's idle. Looking at a
packet trace, after 120secs the shuffle manager is sending a FIN packet to the driver.   The
only way to delay this is to increase spark.shuffle.io.connectionTimeout=3600s on the shuffle
manager.
> I patched the MesosExternalShuffleClient (and ExternalShuffleClient) with newbie Scala
skills to call the TransportContext call with closeIdleConnections "false" and this didn't
help (hadn't done the network trace first).



--
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