[jira] [Commented] (PARQUET-654) Make record-level filtering optional

["Hyukjin Kwon (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/PARQUET-654?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16249333#comment-16249333 ] 

Hyukjin Kwon commented on PARQUET-654:
--------------------------------------

Hi [~rdblue], Is it backported to 1.8.2 as well? Looks I am seeing it in https://github.com/apache/parquet-mr/blob/apache-parquet-1.8.2/parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetInputFormat.java#L122 

> Make record-level filtering optional
> ------------------------------------
>
>                 Key: PARQUET-654
>                 URL: https://issues.apache.org/jira/browse/PARQUET-654
>             Project: Parquet
>          Issue Type: Improvement
>          Components: parquet-mr
>            Reporter: Cheng Lian
>            Assignee: Ryan Blue
>             Fix For: 1.9.0
>
>
> For some engines, especially those with vectorized Parquet readers, filter predicate can often be evaluated more efficiently by the engine. In these cases, Parquet record-level filtering may even slow down query execution when filter push-down is enabled. On the other hand, when the data is well prepared, filter push-down can be very valuable due to row group level filtering.
> One possible improvement here is to add a configuration option that makes record-level filtering optional. In this way, the upper-level engine may leverage both Parquet row group level filtering and faster native record-level filtering.



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