Kong Latency Issue with local docker setup

[frosk1]

Is there an existing issue for this?

• I have searched the existing issues

Kong version ($ kong version)

3.9.0

Current Behavior

I was following the official docker setup guides:
https://docs.konghq.com/gateway/3.10.x/install/docker/

To setup a local docker kong conatiner in dbless mode.

I also spawn an nginx container for kong to proxy requests to.

Unfortunately I get a huge 40seconds latency (X-Kong-Proxy-Latency: 40020) see here:

curl -i http://localhost:8000/mock -H "Connection: close"

HTTP/1.1 200 OK
Content-Type: text/html; charset=UTF-8
Content-Length: 615
Connection: close
Server: nginx/1.27.4
Date: Fri, 04 Apr 2025 23:12:31 GMT
Last-Modified: Wed, 05 Feb 2025 11:06:32 GMT
ETag: "67a34638-267"
Accept-Ranges: bytes
X-Kong-Upstream-Latency: 1
**X-Kong-Proxy-Latency: 40020**
Via: 1.1 kong/3.9.0
X-Kong-Request-Id: f8c007238db998260a2d6957e9c83a32

Expected Behavior

only seeing a few ms for this.

Steps To Reproduce

1. Ubuntu 22.04.5 LT
2. Kong 3.9.0 docker image
3. Start kong docker via:

docker run -d --rm --name kong-dbless \
--network=kong-net \
-v "$(pwd):/kong/declarative/" \
-e "KONG_DATABASE=off" \
-e "KONG_DECLARATIVE_CONFIG=/kong/declarative/kong.yml" \
-e "KONG_PROXY_ACCESS_LOG=/dev/stdout" \
-e "KONG_ADMIN_ACCESS_LOG=/dev/stdout" \
-e "KONG_PROXY_ERROR_LOG=/dev/stderr" \
-e "KONG_ADMIN_ERROR_LOG=/dev/stderr" \
-e "KONG_ADMIN_LISTEN=0.0.0.0:8001" \
-e "KONG_ADMIN_GUI_URL=http://localhost:8002" \
-p 8000:8000 \
-p 8443:8443 \
-p 8001:8001 \
-p 8444:8444 \
-p 8002:8002 \
-p 8445:8445 \
-p 8003:8003 \
-p 8004:8004 \
kong:3.9.0

4. with kong declarative config like this:

_format_version: "3.0"
_transform: true

services:
  - name: example_service
    host: echo-nginx
    port: 80
    protocol: http
    routes:
      - name: example_route
        paths:
          - /mock
        strip_path: true

4. start nginx echo via:

docker run -d --rm --name echo-nginx --network kong-net -p 2082:80 nginx

5. perform curl:

curl -i http://localhost:8000/mock

Anything else?

I dont know whats going on in Kong, the upstream service is not the issue according to the curl outcome. stale or zombi tcp things are also not going on I literally checked everything there, also no hanging connections as well...

Can someone help here, what is happening where do those 40s come from?

[keskinege]

Can you start docker with debug, and see if there are some more info like DNS lookups, etc that blocks?

[frosk1]

will try that