[jira] [Created] (BEAM-2831) Possible bug in Beam+Flink memory management, disk spillover

["Reinier Kip (JIRA)" <ji...@apache.org>]

Reinier Kip created BEAM-2831:
---------------------------------

             Summary: Possible bug in Beam+Flink memory management, disk spillover
                 Key: BEAM-2831
                 URL: https://issues.apache.org/jira/browse/BEAM-2831
             Project: Beam
          Issue Type: Bug
          Components: runner-flink
    Affects Versions: 2.1.0, 2.0.0
         Environment: Flink 1.2.1 and 1.3.0, Java 8, macOS 10.12.6 and RedHat 6
            Reporter: Reinier Kip
            Assignee: Aljoscha Krettek


I’ve been running a Beam pipeline on Flink. Depending on the dataset size and the heap memory configuration of the jobmanager and taskmanager, I may run into an EOFException, which causes the job to fail.

As [discussed on Flink's mailinglist|http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/EOFException-related-to-memory-segments-during-run-of-Beam-pipeline-on-Flink-td15255.html] (stacktrace enclosed), Flink catches these EOFExceptions and activates disk spillover. Because Beam wraps these exceptions, this mechanism fails, the exception travels up the stack, and the job aborts.

EOFException occurs with fairly small datasets (tens of megabytes), 768MiB of Flink heap memory, Beam 2.0.0/2.1.0, Flink 1.2.1/1.3.0, Java 8.

Hopefully this is enough information and this is something that can be adjusted for in Beam. I'd be glad to provide more information where needed.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)