alamb commented on PR #5322: URL: https://github.com/apache/arrow-datafusion/pull/5322#issuecomment-1441830445
> Regarding Join pruning, in batch SQL systems, this is usually achieved by Runtime Filters or Dynamic Filters(constructed dynamically during plan time), we also call this Join pushdown, to prune the rows that fall outside the range of possible join key. Another term from the database literature for this concept I believe is "Sideways information passing" -- the canonical paper is https://www.researchgate.net/publication/45597527_Sideways_Information_Passing_for_Push-Style_Query_Processing I like to think of this as the hash table created for a hash join is passed to the scan, and during the scan rows that would be filtered out of the join (because there are no matching keys) are filtered during the scan. While a neat optimization, I am not sure it is relevant for the usecase of this PR -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
