platinumhamburg commented on issue #1332: URL: https://github.com/apache/fluss/issues/1332#issuecomment-3100492098
@polyzos I think both the test workload, test scenarios and the test environment should be configurable and pluggable. @michaelkoepf I think proposed solution seems quite mature and comprehensive. It offers a powerful and flexible framework that allows us to measure all key aspects of our engine, such as throughput, latency, fault tolerance recovery time, CPU/MEM/IO/disk/thread consumption, compaction, tiering speed, and more. Although it may be a bit heavy, it's definitely worth exploring. Additionally, I believe @xx789633 's proposal is also valuable. Hologres and Flink share many overlapping features in streaming storage scenarios, such as fixed queries and binlogs. The holo-e2e-performance-tool provides us with a lightweight yet effective way to evaluate our performance. It's simple but practical, and we definitely need it—we can't wait for your work to be completed. -- 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]
