yydance commented on issue #11154: URL: https://github.com/apache/apisix/issues/11154#issuecomment-2066203035
@hanqingwu @nitishfy I find out the reason. When I enable prometheus plugin, then I use wrk to test, below ``` # wrk -t8 -c500 -d60s -s ./get.lua http://10.252.228.254:61160/infra/health/ping ``` And the result: ``` Running 1m test @ http://10.252.228.254:61160/infra/health/ping 8 threads and 500 connections Thread Stats Avg Stdev Max +/- Stdev Latency 14.33ms 29.20ms 197.79ms 87.44% Req/Sec 80.82 69.02 370.00 78.42% 1123 requests in 1.00m, 355.40KB read Requests/sec: 18.69 Transfer/sec: 5.92KB ``` Then apisix pod cpu is full even though I stop the requests. Prometheus configuration: ``` prometheus: enabled: true containerPort: 9091 metricPrefix: "apisix_" path: "/apisix/prometheus/metrics" ``` -- 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]
