xiangfu0 opened a new pull request, #19713: URL: https://github.com/apache/pinot/pull/19713
Port the join-only work from #19122 onto the leaf stack, with shared sorted receives, resumable duplicate output and prompt buffer release. INNER/LEFT joins preserve the left join-key ASC NULLS LAST prefix; `maxRowsInJoin` bounds duplicate-run storage rather than total emitted rows. Try `SELECT /*+ joinOptions(join_strategy='sorted') */ a.id, b.id FROM myTable a JOIN myTable b ON a.id=b.id;`. Hash joins stay the default; bounded output blocks preserve cancellation and LIMIT progress. Planner/serde, focused join tests and H2 result comparisons pass, with scoped style/license checks. Parent: https://github.com/apache/pinot/pull/19712; broader mixed-version, skew benchmarks and full pipeline memory bounds remain pending. #19122 stays open for author coordination. -- 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]
