Dandandan commented on issue #18489: URL: https://github.com/apache/datafusion/issues/18489#issuecomment-4601578917
> Indeed -- q23 is entirely about pushdown (and the duckdb plan last I looked bas some horrible left join rewrite) I think a join rewrite (or an improved late materialization) is probably an improvement though over "just" dynamic filters as it avoids scanning the non-top-k rows for most of the data / columns (in the early scanning phase with non-informative dynamic filter). We can do better though by pushing down the row ids to parquet instead (compute top k on columns, then only scan top k row-ids). It looks like DuckDB also supports this (not sure if it also does it for Q23)? https://github.com/duckdb/duckdb/pull/17325 https://www.vldb.org/pvldb/vol18/p4616-liu.pdf -- 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]
