Dandandan commented on code in PR #16433: URL: https://github.com/apache/datafusion/pull/16433#discussion_r2186106170
########## datafusion/physical-plan/src/topk/mod.rs: ########## @@ -319,19 +342,75 @@ impl TopK { /// (a > 2 OR (a = 2 AND b < 3)) /// ``` fn update_filter(&mut self) -> Result<()> { - let Some(filter) = &self.filter else { + // If the heap doesn't have k elements yet, we can't create thresholds + let Some(max_row) = self.heap.max() else { return Ok(()); }; - let Some(thresholds) = self.heap.get_threshold_values(&self.expr)? else { - return Ok(()); + + let new_threshold_row = &max_row.row; + + // Extract filter expression reference before entering critical section + let filter_expr = Arc::clone(&self.filter.expr); + + // Check if we need to update and do both threshold and filter update atomically + { + let mut threshold_guard = self.filter.threshold_row.write(); + if let Some(current_row) = threshold_guard.as_ref() { + match current_row.as_slice().cmp(new_threshold_row) { + Ordering::Greater => { + // new < current, so new threshold is more selective Review Comment: I think this was wrong before @adriangb - in the heap lower means more selective -- 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...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org