showuon edited a comment on pull request #10552: URL: https://github.com/apache/kafka/pull/10552#issuecomment-822200511
The performance comparison in jenkins for uniform subscription and non-equal subscription with the setting: ``` topicCount = 500; partitionCount = 2000; consumerCount = 2000; ``` ``` Build / JDK 15 and Scala 2.13 / testLargeAssignmentAndGroupWithNonEqualSubscription() | 13 sec | Passed Build / JDK 11 and Scala 2.13 / testLargeAssignmentAndGroupWithNonEqualSubscription() | 17 sec | Passed Build / JDK 8 and Scala 2.12 / testLargeAssignmentAndGroupWithNonEqualSubscription() | 14 sec | Passed Build / JDK 8 and Scala 2.12 / testLargeAssignmentAndGroupWithUniformSubscription() | 3.4 sec | Passed Build / JDK 15 and Scala 2.13 / testLargeAssignmentAndGroupWithUniformSubscription() | 3.3 sec | Passed Build / JDK 11 and Scala 2.13 / testLargeAssignmentAndGroupWithUniformSubscription() | 3.9 sec | Passed ``` I think after this PR, the performance is acceptable for non-equal subscription cases. We can have incremental improvement in the following stories. Thank you. -- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org