nzw921rx commented on issue #12058: URL: https://github.com/apache/seatunnel/issues/12058#issuecomment-5557075198
Thanks for the investigation work so far. I have expanded #12086 with a step-by-step investigation methodology: https://github.com/apache/seatunnel/issues/12086#investigation-methodology To clarify the expectations for this issue: the immediate goal is to explain the reported variance through reproducible evidence. There is no expectation to submit a code change or PR immediately. Please start with one affected parameter combination from the existing benchmark, retain its measurement settings, and investigate how the anomalous iterations relate to specific runtime behavior. A consistent local environment is sufficient for initial reproduction and controlled experiments. Reproduction results, runtime observations, ruled-out hypotheses, and questions are all welcome here before a PR is ready. Existing experiments remain useful inputs; there is no need to restart work that already provides relevant evidence. We can discuss those findings first, then decide whether a benchmark correction, production change, or additional diagnostic capability is needed. Any proposed change should explain how it addresses the original symptom and preserve the relevant runtime guarantees. -- 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]
