anandheritage commented on PR #15844: URL: https://github.com/apache/pinot/pull/15844#issuecomment-2894996832
> > In distributed group-by queries that apply a LIMIT without an accompanying ORDER BY clause, each server arbitrarily selects a subset of groups, which can lead to non-deterministic behavior and inconsistent final aggregations when the total number of groups exceeds the limit; this randomness in group selection may omit important groups from the final result and compromise query accuracy, thereby necessitating a deterministic mechanism that ensures all non-ordering group keys are uniformly considered across all servers to guarantee the correctness and consistency of the aggregated output. > > Why is that an issue? The fact that there is no deterministic order is a feature in terms of performance, don't you think? The issue is incorrect result for this kind of cases : https://github.com/apache/pinot/issues/14956 -- 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
