orpiske commented on PR #9968: URL: https://github.com/apache/camel/pull/9968#issuecomment-1530980188
> By chance do you have any benchmarks to share? Yes I do. I am preparing a blog post with the details, methodology, etc. But here's a preview for the disruptor (in just few of the many other scenarios): Obs.: the notation is inverted and the baseline is the code is the code with this patch and the test code is the test with 4.0.0-M1. *25 consumers + 25 producers*: ``` GEOMETRIC MEAN (RATE): Test: 640260.6763745428 | Baseline: 712828.9356009845 Delta: -72568.25922644173 The geometric mean rate was lower for the test than for the baseline ``` *10 consumers + 9 producers*: ``` GEOMETRIC MEAN (RATE): Test: 767544.7450252476 | Baseline: 841304.9248985515 Delta: -73760.17987330398 The geometric mean rate was lower for the test than for the baseline ``` *7 consumers + 3 producers*: ``` GEOMETRIC MEAN (RATE): Test: 486716.1190278101 | Baseline: 610061.3909864418 Delta: -123345.27195863164 The geometric mean rate was lower for the test than for the baseline ``` All in all, the new code tends to be faster in around 95% of the cases. The results from JMH also indicate the code being faster (i.e.; having a higher score in ops/ms - IIRC), although I don't have them easily at hand right now. -- 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: commits-unsubscr...@camel.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
