[
https://issues.apache.org/jira/browse/SPARK-44684?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
GANHONGNAN updated SPARK-44684:
-------------------------------
Remaining Estimate: 2,016h (was: 0.05h)
Original Estimate: 2,016h (was: 0.05h)
> Runtime min-max filter
> ----------------------
>
> Key: SPARK-44684
> URL: https://issues.apache.org/jira/browse/SPARK-44684
> Project: Spark
> Issue Type: New Feature
> Components: SQL
> Affects Versions: 3.2.1
> Reporter: GANHONGNAN
> Priority: Major
> Labels: performance
> Original Estimate: 2,016h
> Remaining Estimate: 2,016h
>
> We can infer min-max index when building bloom filter and push it down to
> datasource.
> # Min-max index can skip part of data before loading them into memory.
> # building min-max index can be done along with bloom filter building, so
> aggregation for bloom filter building can be reused.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
