[jira] [Updated] (SPARK-34939) Throw fetch failure exception when unable to deserialize broadcasted map statuses

["L. C. Hsieh (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/SPARK-34939?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

L. C. Hsieh updated SPARK-34939:
--------------------------------
    Summary: Throw fetch failure exception when unable to deserialize broadcasted map statuses  (was: Throw fetch failure exception when unable to deserialize map statuses)

> Throw fetch failure exception when unable to deserialize broadcasted map statuses
> ---------------------------------------------------------------------------------
>
>                 Key: SPARK-34939
>                 URL: https://issues.apache.org/jira/browse/SPARK-34939
>             Project: Spark
>          Issue Type: Bug
>          Components: Spark Core
>    Affects Versions: 2.4.7, 3.0.2, 3.2.0, 3.1.1
>            Reporter: L. C. Hsieh
>            Priority: Major
>
> One customer encountered application error. From the log, it is caused by accessing non-existing broadcasted value. The broadcasted value is map statuses. There is a race-condition.
> After map statuses are broadcasted and the executors obtain serialized broadcasted map statuses. If any fetch failure happens after, Spark scheduler invalidates cached map statuses and destroy broadcasted value of the map statuses. Then any executor trying to deserialize serialized broadcasted map statuses and access broadcasted value, {{IOException}} will be thrown. Currently we don't catch it in {{MapOutputTrackerWorker}} and above exception will fail the application.
> Normally we should throw a fetch failure exception for such case and let Spark scheduler handle this.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

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