xicm commented on issue #11288: URL: https://github.com/apache/hudi/issues/11288#issuecomment-2129890980
Some tests ``` package org.example; import java.util.ArrayList; import java.util.Comparator; import java.util.List; public class Test { public static void main(String[] args) { List<Integer> list1 = new ArrayList<Integer>(); List<Integer> list2 = new ArrayList<Integer>(); List<Integer> list3 = new ArrayList<Integer>(); List<Integer> list4 = new ArrayList<Integer>(); List<Integer> list5 = new ArrayList<Integer>(); List<Integer> list6 = new ArrayList<Integer>(); System.out.println("bucket_num % parallelism"); for (int i = 0; i < 20; i++) { list1.add(i % 20); } for (int i = 0; i < 20; i++) { list1.add(i % 20); } list1.sort(Comparator.naturalOrder()); for (int n : list1) { System.out.print(n); System.out.print(" "); } System.out.println(); System.out.println("Hash(partition + bucket_num) % parallelism"); System.out.println("parallelism = 20"); for (int i = 0; i < 20; i++) { list2.add((("part1" + i).hashCode() & Integer.MAX_VALUE) % 20); } for (int i = 0; i < 20; i++) { list2.add((("part2" + i).hashCode() & Integer.MAX_VALUE) % 20); } list2.sort(Comparator.naturalOrder()); for (int n : list2) { System.out.print(n); System.out.print(" "); } System.out.println(); System.out.println("(Hash(partition) + bucket_num) % parallelism"); System.out.println("parallelism = 20"); for (int i = 0; i < 20; i++) { list3.add((("part1".hashCode() & Integer.MAX_VALUE) + i) % 20); } for (int i = 0; i < 20; i++) { list3.add((("part2".hashCode() & Integer.MAX_VALUE) + i) % 20); } list3.sort(Comparator.naturalOrder()); for (int n : list3) { System.out.print(n); System.out.print(" "); } System.out.println(); System.out.println("(Hash(partition) % parallelism + bucket_num) % parallelism"); System.out.println("parallelism = 20"); for (int i = 0; i < 20; i++) { list4.add((("part1".hashCode() & Integer.MAX_VALUE) + i) % 20); } for (int i = 0; i < 20; i++) { list4.add((("part2".hashCode() & Integer.MAX_VALUE) + i) % 20); } list4.sort(Comparator.naturalOrder()); for (int n : list4) { System.out.print(n); System.out.print(" "); } System.out.println(); System.out.println("(Hash(partition) % parallelism + bucket_num) % parallelism"); System.out.println("parallelism = 40"); // bucket_num = 20, parallelism = 40 for (int i = 0; i < 20; i++) { list5.add((("part1".hashCode() & Integer.MAX_VALUE) % 40 + i) % 40); } for (int i = 0; i < 20; i++) { list5.add((("part2".hashCode() & Integer.MAX_VALUE) % 40 + i) % 40); } list5.sort(Comparator.naturalOrder()); for (int n : list5) { System.out.print(n); System.out.print(" "); } System.out.println(); System.out.println("(Hash(partition) % parallelism * bucket_num + bucket_num) % parallelism"); System.out.println("parallelism = 40"); for (int i = 0; i < 20; i++) { list6.add((("part1".hashCode() & Integer.MAX_VALUE) % 40 * 20 + i) % 40); } for (int i = 0; i < 20; i++) { list6.add((("part2".hashCode() & Integer.MAX_VALUE) % 40 * 20 + i) % 40); } list6.sort(Comparator.naturalOrder()); for (int n : list6) { System.out.print(n); System.out.print(" "); } } } ``` ![image](https://github.com/apache/hudi/assets/36392121/ae1f9588-9eff-4560-94ed-f6e59fe39b57) -- 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...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org