In this benchmark, druid was killed and restarted after every query because druid seems to get into a degraded state otherwise. Very very likely that there is something wrong with the druid setup here. It would have been useful to know basic details such as druid version.

You can see that setup used is the one provided in a package: single-server/medium. It makes sense to improve setup, but I recommend to provide better configuration by default. I think it is a common courtesy that system should just work at most cases without hard tuning.