You are viewing a plain text version of this content. The canonical link for it is here.
Posted to notifications@apisix.apache.org by GitBox <gi...@apache.org> on 2022/09/15 04:13:08 UTC

[GitHub] [apisix] ryan4yin commented on issue #7919: bug: P99 latency is too high

ryan4yin commented on issue #7919:
URL: https://github.com/apache/apisix/issues/7919#issuecomment-1247559041

   > 1. The sample is so small that you can reproduce the sample.
   > 2. Is there a prometheus exporter that visits http://127.0.0.1:9091/apisix/prometheus/metrics to get the metrics when the flame chart is sampled?
   > 3. From the latency monitoring, APISIX causes high latency, you can remove the `proxy-mirror` plugin and keep only `prometheus` plugin, and test again?
   
   1. I'm trying to reproduce this in a test environment
   2. I tried several times to sample a cpu flame chart, I post some of them below.
   3. I disabled the `proxy-mirror` plugin, but it's helpless, the P99 latency is still high.
   
   the flame chart smapled 16mins ago, all the cpu flame chart seems the same:
   
   <img width="1455" alt="image" src="https://user-images.githubusercontent.com/22363274/190312062-959f5803-fad7-4a67-9425-51c8394ad381.png">
   
   but the lua exectution flame chart shows some new info:
   
   <img width="1496" alt="image" src="https://user-images.githubusercontent.com/22363274/190312183-5aac1efe-bbc1-48c9-9277-d2de631fda87.png">
   
   


-- 
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: notifications-unsubscribe@apisix.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org