nzw921rx commented on PR #12081: URL: https://github.com/apache/seatunnel/pull/12081#issuecomment-5535668827
First of all, thank you for picking up this task so quickly and submitting the PR. I have a couple of suggestions: 1. I think we should first build a complete evidence chain locally and include it in the PR description. This could include before/after flame graphs for Wall, CPU, and Lock profiling. If GC is involved, the relevant GC profiling results should also be included. The goal is to establish a clear and complete causal chain from the observed performance issue, through profiling and root-cause analysis, to the optimization itself. 2. Please also include a comparison of the local results before and after the optimization. This is not limited to GC or CPU metrics; it could also include improvements in throughput, error margin, CV, allocation rate, or any other metrics relevant to this particular issue. Having this evidence documented clearly in the PR will make it much easier for us to understand and evaluate the optimization. It will also help us reproduce the same experiment locally and independently verify the results. -- 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]
