idbeta commented on issue #3391: URL: https://github.com/apache/apisix/issues/3391#issuecomment-766729062
After more than 10 tests, I determined that the test environment provided by github action is random, sometimes the performance is better, sometimes the performance is worse, the following is the result of my tests, all results are for testing only single core: ``` APISIX QPS CPU performance Division result 21331 3620 5.892541436464088 21150 3424 6.176985981308411 23533 4122 5.709121785541 23739 3965 5.987137452711223 23093 3463 6.668495524112042 23149 3408 6.792546948356808 16586 3791 4.375098918491163 28767 4482 6.418340026773762 22673 3735 6.07041499330656 25898 4126 6.276781386330587 13530 3393 3.98762157382847 20307 3416 5.944672131147541 23424 4214 5.558614143331751 ``` The machine environment corresponding to these results is as follows (obtained by `cat /proc/cpuinfo | grep'model name'`): ``` model name : Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz model name : Intel(R) Xeon(R) CPU E5-2673 v3 @ 2.40GHz model name : Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz model name : Intel(R) Xeon(R) Platinum 8272CL CPU @ 2.60GHz ``` It can be seen that the environment of each test is different, so the test results are not comparable. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
