Having administered Druid for several years, ClickHouse's supposed simplicity is definitely appealing were I to start a new project with similar requirements. Then again, back then, I needed Petabyte scale and > 1 million inserts/sec and ClickHouse couldn't do it.

I managed to do 5m/s in a single server. Something must be off.

Depends on how big your structs are coming in, how you are holding on to the data, and what else you are doing with it on ingestion.

I've been using ClickHouse in production to do things I just couldn't do with any other technology, it's not only simpler.