nzw921rx commented on PR #12172:
URL: https://github.com/apache/seatunnel/pull/12172#issuecomment-5570548684

   <img width="2048" height="1212" alt="image" 
src="https://github.com/user-attachments/assets/9ee46d0d-fb66-4503-a4b6-e1fc937aadea";
 />
   
   Thanks for sharing the benchmark results. Overall, the throughput 
improvements on both Java 8 and Java 11 look quite significant.
   
   I noticed that the CV and Error increased across all four scenarios on Java 
11. Although the absolute values are still relatively low, the trend appears 
fairly consistent. Would it be possible to add a few more ABBA runs to confirm 
whether this increase is reproducible?
   
   If the same trend remains, it may also be helpful to compare the 
profiling/runtime data between the baseline and candidate on Java 11, and check 
whether the change is related to allocation, GC, synchronization, blocking, or 
other runtime behavior. This would help us determine whether it is normal 
measurement variation or a stability change introduced by this optimization.


-- 
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: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to