thin haven
Hey guys, running into an issue that I'm not sure if it's CFW or me.
Context:
I'm just using CFW as middleware to authenticate session tokens using Jose. That's the only thing my instance is doing. The request is to the worker like /llm/request to be able to get a response back.
**Specifics: **
The problem I'm running into is that for some reason, extremely randomly, the client-side time to get a response back is really really slow, like 5-6 seconds, even though wall time for that same request is 200ms or so.
**Here's an example of what I've logged from one of these faulty requests: **
Server-Side:
Wall time (233ms)
Request from upstream provider (LLM Inference) - (181ms)
Client-Side:
While connecting
🔎 summary | reused:0 proto:h3 dns:1ms tcp:118ms tls:117ms server:2918ms total:3154ms
-> Reused indicates if this was a previously open connection.
I'm confused how server ends up being around 2918 ms, even though the wall time is 233 ms?
mint spindle