walterddr opened a new pull request, #9100: URL: https://github.com/apache/pinot/pull/9100
During multi-stage query engine planning. We knew exactly what data partition each server has by looking into the exchange logics. Thus we should use this to optimize data shuffling. This PR - adds partition key analysis - populate partition keys across `InputRef` across nodes - analyzes partition keys for partition desire to eliminate unnecessary shuffling NOT in this PR - skip data shuffle entirely. this can be done by later implementation of the direct transferable block util -- 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: commits-unsubscr...@pinot.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org
