rkrishn7 commented on issue #17171:
URL: https://github.com/apache/datafusion/issues/17171#issuecomment-3269086198

   Thanks for the thorough thoughts/info @adriangb!
   
   I'm wondering if there are effectively multiple optimizations that we can 
take advantage of here.
   
   I think building an `IN LIST` in the dynamic filter (in addition to min/max) 
allows us to leverage the existing machinery that builds literal guarantees in 
`PruningPredicate`. The parquet data source already takes advantage of this in 
the case that bloom filters are present and can help us prune entire row 
groups, which definitely seems valuable to me.
   
   Additionally, your point around building a bloom filter to pushdown as 
another `PhysicalExpr` also makes a lot of sense to me. Since this would 
(likely) let us save on more decode cycles.
   
   Does that sound right to you?


-- 
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]

Reply via email to