lyang24 commented on issue #20324: URL: https://github.com/apache/datafusion/issues/20324#issuecomment-3894595612
want to chime in on query 14
```
SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c
FROM hits
WHERE "SearchPhrase" <> ''
GROUP BY "SearchEngineID", "SearchPhrase"
ORDER BY c DESC
LIMIT 10;
```
searchPharse != ' ' its very hard for parquet stats to skip those type of
filters (usually i am thinking about min/max states to filter) very likely this
is not going to skip data pages and the benefit of pushing down predicate might
be lost here.
wonder if there are ways to route the push down vs fliter exec path?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
