Xiaochen Wang

hi @woshitianbz could you show the dns response to help developers to debug if there is no sensible information You could log it with some dns client tool like `$...

> xxxxxxxx-xx-xxxxx.xxx-x-xxxxxx.x.xx.xxxx.xxxxxx.xxxxxx.xxxxx After a lot of efforts, I cannot reproduce the issue. You may need to provide a precise method to reproduce this problem. Based on the information provided, I...

I think you could upgrade to 2.8 firstly, which contains so many bugfixes. > 2024/07/26 03:33:06 [error] 22940#0: *228411 upstream prematurely closed connection while reading response header from upstream, client:...

I think you could not control response buffering via `nginx_proxy_proxy_buffering = off `, because kong has already abstract this function in its nginx location {} block, although you could use...

hi @vpilania, have you resolved this issue?

hi, could you try this command to verify whether the file could be downloaded as the error log mentioned. ``` $ curl https://luafr.org/luarocks/manifest-5.1 You could also try accessing other manifiest...

Hi @jrosal06 Out of topic, I think before you post your raw data of tcpdump info, you need to explain the detailed of your tcpdump info. I felt quite frustrated...

> We want your help to know if in Kubernetes versions cluster greater than 1.27 (OpenShift 4.14) some parameter should be adjusted in Kong to mitigate and clear this alarm...

hi @jrosal06 After re-reviewing your tcpdump info and your kong log message, i found some new interesting thing, which might give you some hints to troubleshoot further. From your tcpdump...

Could you use a Redis client tool to check if Redis is operational during the time you're benchmarking Kong? Based on the information you provided, we can't determine where the...