[
https://issues.apache.org/jira/browse/BEAM-7574?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ismaël Mejía updated BEAM-7574:
-------------------------------
Description:
Combine.perKey on current implementation uses technique of creating an
accumulator for each input key and then merge all these accumulators together.
Optimize this by:
* changing accumulator from Iterable to Map, and using addInput as much as
possible
* try to move the window explode to pre-shuffle (add window label to key for
non-merging windows), measure the impact, and if the impact is substantial,
implement that for at least window functions assigning to single (global)
window or single window per element (tumbling windows)
was:
Combine.perKey on current implementation uses technique of creating an
accumulator for each input key and then merge all these accumulators together.
Optimize this by:
* changing accumulator from Iterable to Map, and using addInput as much as
possible
* try to move the window explode to pre-shuffle (add window label to key for
non-merging windows), measure the impact, and if the impact is substantial,
implement that for at leasit window functions assigning to single (global)
window or single window per element (tumbling windows)
> Spark runner: Combine.perKey performance issues
> -----------------------------------------------
>
> Key: BEAM-7574
> URL: https://issues.apache.org/jira/browse/BEAM-7574
> Project: Beam
> Issue Type: Improvement
> Components: runner-spark
> Affects Versions: 2.13.0
> Reporter: Jan Lukavský
> Assignee: Jan Lukavský
> Priority: Major
> Fix For: 2.15.0
>
> Time Spent: 10h
> Remaining Estimate: 0h
>
> Combine.perKey on current implementation uses technique of creating an
> accumulator for each input key and then merge all these accumulators
> together. Optimize this by:
> * changing accumulator from Iterable to Map, and using addInput as much as
> possible
> * try to move the window explode to pre-shuffle (add window label to key for
> non-merging windows), measure the impact, and if the impact is substantial,
> implement that for at least window functions assigning to single (global)
> window or single window per element (tumbling windows)
--
This message was sent by Atlassian Jira
(v8.3.2#803003)
