[jira] [Updated] (BEAM-8848) Flink: Memory efficient GBK implementation for batch runner

["Maximilian Michels (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/BEAM-8848?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Maximilian Michels updated BEAM-8848:
-------------------------------------
    Status: Open  (was: Triage Needed)

> Flink: Memory efficient GBK implementation for batch runner
> -----------------------------------------------------------
>
>                 Key: BEAM-8848
>                 URL: https://issues.apache.org/jira/browse/BEAM-8848
>             Project: Beam
>          Issue Type: Improvement
>          Components: runner-flink
>            Reporter: David Moravek
>            Assignee: David Moravek
>            Priority: Major
>
> In current batch runner, all the values for a single key need to fit in memory, because the resulting GBK iterable is materialized using "List" data structure.
> Implications:
> - This blocks user from using custom sharding in most of the IOs, as the whole shard needs to fit in memory.
> - Frequent OOM failures in case of skewed data (pipeline should be running slow instead of failing). This is super hard to debug for inexperienced user.
> We can do way better for non-merging windows, the same way we do for Spark runner. Only drawback is, that this implementation does not support result re-iterations. We'll support turning this implementation on and off, if user needs to trade off reiterations for memory efficiency.



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