SEZ9 commented on issue #13048: URL: https://github.com/apache/seatunnel/issues/13048#issuecomment-6486654788
Thanks for the detailed analysis. The 1 s steps in the scores and the `waitUntilLoaded()` / `waitAllTrue()` explanation are convincing, and the three goals you listed make sense as scope. One request before work starts: I could not find `IMapDagStorageBenchmark`, `IMapJobStorageBenchmark`, or `IMapWalStorageBenchmark` in the repository. Could you point to the module, branch, or PR where these classes and the benchmark workflow that produced the linked action runs live? For goal 1, a wall-clock profile (not CPU) of a single `recoverAll` / `finishedJobDagLoad` iteration showing time in `waitAllTrue` vs. the actual load would be a good first deliverable; until then, comparisons like the 4.06 s vs 3.05 s `recoverAll` result should be treated as inconclusive. <!-- streview-comment:2112 --> -- 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]
