Johannes Rudolph
Johannes Rudolph
Thanks, @strelec, that might make sense (but there might be some reasons it was done the way it is). Would you like to create a PR for that feature?
Thanks, @GKuldeepak-Knoldus. Yes, this issue is still up for grabs, so please go ahead!
> Can only update when drop java 11. Good to know, thanks. Let's revisit when we decide if we keep supporting Java 8 on 10.3.x.
Thanks for the report and reproducer, @AvaPL. It doesn't seem that there's an actual leak but it seems something is wrong with the buffer size calculation in `PoolInterface`. It assumes...
Good to hear! The backpressure log message is internal and probably spurious and won't have any real effect.
> It isn't spurious. It's clearly visible that after the backpressure kicks in, the time between "Dispatching request [POST /_bulk Strict(815 bytes)] to pool" and the actual request is at...
Sorry, forget to answer here. I had a try at reproducing this but for me it works as expected (when running requests against a host that just drops SYN packets...
Hi @idoMajor41, you can look at the documentation of the `base-connection-backoff` setting in the reference.conf. It shows our handling of connection attempts. In particular, after a failure we do exponential...
Hi @TiDiCom, thanks for the report. Do you have any indications why this would be the case? How did you find out that this would be a bottleneck? It seems...
I would suggest checking response times of the proxy on the application server with tcpdump. This way you can rule out that it is the proxy itself which is slow.